Computational model used in machine learning, based on connected, hierarchical functions
POPULARITY
Analysis of image classifiers demonstrates that it is possible to understand backprop networks at the task-relevant run-time algorithmic level. In these systems, at least, networks gain their power from deploying massive parallelism to check for the presence of a vast number of simple, shallow patterns. https://betterwithout.ai/images-surface-features This episode has a lot of links: David Chapman's earliest public mention, in February 2016, of image classifiers probably using color and texture in ways that "cheat": twitter.com/Meaningness/status/698688687341572096 Jordana Cepelewicz's “Where we see shapes, AI sees textures,” Quanta Magazine, July 1, 2019: https://www.quantamagazine.org/where-we-see-shapes-ai-sees-textures-20190701/ “Suddenly, a leopard print sofa appears”, May 2015: https://web.archive.org/web/20150622084852/http://rocknrollnerd.github.io/ml/2015/05/27/leopard-sofa.html “Understanding How Image Quality Affects Deep Neural Networks” April 2016: https://arxiv.org/abs/1604.04004 Goodfellow et al., “Explaining and Harnessing Adversarial Examples,” December 2014: https://arxiv.org/abs/1412.6572 “Universal adversarial perturbations,” October 2016: https://arxiv.org/pdf/1610.08401v1.pdf “Exploring the Landscape of Spatial Robustness,” December 2017: https://arxiv.org/abs/1712.02779 “Overinterpretation reveals image classification model pathologies,” NeurIPS 2021: https://proceedings.neurips.cc/paper/2021/file/8217bb4e7fa0541e0f5e04fea764ab91-Paper.pdf “Approximating CNNs with Bag-of-Local-Features Models Works Surprisingly Well on ImageNet,” ICLR 2019: https://openreview.net/forum?id=SkfMWhAqYQ Baker et al.'s “Deep convolutional networks do not classify based on global object shape,” PLOS Computational Biology, 2018: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1006613 François Chollet's Twitter threads about AI producing images of horses with extra legs: twitter.com/fchollet/status/1573836241875120128 and twitter.com/fchollet/status/1573843774803161090 “Zoom In: An Introduction to Circuits,” 2020: https://distill.pub/2020/circuits/zoom-in/ Geirhos et al., “ImageNet-Trained CNNs Are Biased Towards Texture; Increasing Shape Bias Improves Accuracy and Robustness,” ICLR 2019: https://openreview.net/forum?id=Bygh9j09KX Dehghani et al., “Scaling Vision Transformers to 22 Billion Parameters,” 2023: https://arxiv.org/abs/2302.05442 Hasson et al., “Direct Fit to Nature: An Evolutionary Perspective on Biological and Artificial Neural Networks,” February 2020: https://www.gwern.net/docs/ai/scaling/2020-hasson.pdf
Today we're visiting the beautiful seaside township of St Raphael, nestled in the French Riviera to catch up with our guest the Happy Brains' founder, Neuro Couple's creator and author Dr. Thomas Trautmann. Thomas has a real passion for people and their brains, a bit like a zombie. Driven by people's smiles, he enjoys life with his family, pets, horses, and friends. He speaks fluently English, French, and German, and started his career as a Computer engineer and wrote his Ph.D. thesis Working and improving an Artificial Neural Networks model. So TEAM you may rightly guess where this conversation is heading, but there is a twist. After a while he moved towards the "dark side", towards marketing and sales, wanting to be closer to the decision maker: the client. Thomas has worked for major companies like HP, Bosch, AOL, Steelcase as well as smaller ones before founding his first company. His scientific as well as marketing, sales, and strategy knowledge allowed him to get certified as a Neuro Marketing instructor with SalesBrain. The more he read and studied about the decision processes in the human brain the more he noticed the differences between the male and female brains. After two years of data collection and compilation Thomas launched the Neuro Couple concept and published his first book: "Is there a Brain in Your couple?" With the driving force behind efficient marketing, sales, strategy, and relationships being Persuasion, Thomas is now leading ethical Persuasion Strategies and Techniques. TEAM, Thomas speaks a lot in his work about understanding the differences between the male and female brains and how we can leverage the latest neuroscience to strengthen our marriage and business leadership. Visit our website to access the guest links, full transcript, and episode notes. - Coaching 4 Companies
Neural networks are the backbone of many AI and machine learning systems. But how can they be applied to real-world scenarios?Today's guest is Damian Borth, Professor of Artificial Intelligence & Machine Learning at the University of St. Gallen. He is also the director of the Computer Science Institute at St. Gallen.His work on neural networks has taken him to several subject areas including climate change, financial fraud detection, and text-to-speech. He is also the recipient of a Google Research Scholar Award.We discuss what neural networks are, what they do, and how their application could help us save the world.00:00 - Intro02:02 - Damian's background03:01 - What is a neural network?09:21 - Neural networks and climate change12:44 - Neural networks and text-to-speech14:56 - Bias in AI training data12:44 - Academia and the real world27:12 - Dan's final thoughtsLINKS:Damian Borth: https://www.linkedin.com/in/damianborth/?originalSubdomain=chDan Klein: https://uk.linkedin.com/in/dplkleinZühlke: https://www.zuehlke.com/enWelcome to Data Today, a podcast from Zühlke.We're living in a world of opportunities. But to fully realise them, we have to reshape the way we innovate.We need to stop siloing data, ring-fencing knowledge and looking at traditional value chains. And that's what this podcast is about. Every two weeks, we're taking a look at data outside the box to see how amazing individuals from disparate fields and industries are transforming the way they work with data, the challenges they are overcoming, and what we can all learn from them.Zühlke is a global innovation service provider. We envisage ideas and create new business models for our clients by developing services and products based on new technologies – from the initial vision through development to deployment, production and operation.
Did you know that the concept of deep learning goes way back to the 1950s? However, it is only in recent years that this technology has created a tremendous amount of buzz (and for good reason!). A subset of machine learning, deep learning is inspired by the structure of the human brain, making it fascinating to learn about. In this episode, Lois Houston and Nikita Abraham interview Senior Principal OCI Instructor Hemant Gahankari about deep learning concepts, including how Convolution Neural Networks work, and help you get your deep learning basics right. Oracle MyLearn: https://mylearn.oracle.com/ou/learning-path/become-an-oci-ai-foundations-associate-2023/127177 Oracle University Learning Community: https://education.oracle.com/ou-community LinkedIn: https://www.linkedin.com/showcase/oracle-university/ X (formerly Twitter): https://twitter.com/Oracle_Edu Special thanks to Arijit Ghosh, David Wright, Himanshu Raj, and the OU Studio Team for helping us create this episode. -------------------------------------------------------- Episode Transcript: 00:00 The world of artificial intelligence is vast and everchanging. And with all the buzz around it lately, we figured it was the perfect time to revisit our AI Made Easy series. Join us over the next few weeks as we chat about all things AI, helping you to discover its endless possibilities. Ready to dive in? Let's go! 00:33 Welcome to the Oracle University Podcast, the first stop on your cloud journey. During this series of informative podcasts, we'll bring you foundational training on the most popular Oracle technologies. Let's get started! 00:47 Lois: Hello and welcome to the Oracle University Podcast. I'm Lois Houston, Director of Innovation Programs with Oracle University, and with me is Nikita Abraham, Principal Technical Editor. Nikita: Hi everyone! Lois: Today, we're going to focus on the basics of deep learning with our Senior Principal OCI Instructor, Hemant Gahankari. Nikita: Hi Hemant! Thanks for being with us today. So, to get started, what is deep learning? 01:14 Hemant: Hi Niki and hi Lois. So, deep learning is a subset of machine learning that focuses on training Artificial Neural Networks, abbreviated as ANN, to solve a task at hand. Say, for example, image classification. A very important quality of the ANN is that it can process raw data like pixels of an image and extract patterns from it. These patterns are treated as features to predict the outcomes. Let us say we have a set of handwritten images of digits 0 to 9. As we know, everyone writes the digits in a slightly different way. So how do we train a machine to identify a handwritten digit? For this, we use ANN. ANN accepts image pixels as inputs, extracts patterns like edges and curves and so on, and correlates these patterns to predict an outcome. That is what digit does the image has in this case. 02:17 Lois: Ok, so what you're saying is given a bunch of pixels, ANN is able to process pixel data, learn an internal representation of the data, and predict outcomes. That's so cool! So, why do we need deep learning? Hemant: We need to specify features while we train machine learning algorithm. With deep learning, features are automatically extracted from the data. Internal representation of features and their combinations is built to predict outcomes by deep learning algorithms. This may not be feasible manually. Deep learning algorithms can make use of parallel computations. For this, usually data is split into small batches and processed parallelly. So these algorithms can process large amount of data in a short time to learn the features and their combinations. This leads to scalability and performance. In short, deep learning complements machine learning algorithms for complex data for which features cannot be described easily. 03:21 Nikita: What can you tell us about the origins of deep learning? Hemant: Some of the deep learning concepts like artificial neuron, perceptron, and multilayer perceptron existed as early as 1950s. One of the most important concept of using backpropagation for training ANN came in 1980s. In 1990s, convolutional neural networks were also introduced for image analysis tasks. Starting 2000, GPUs were introduced. And 2010 onwards, GPUs became cheaper and widely available. This fueled the widespread adoption of deep learning uses like computer vision, natural language processing, speech recognition, text translation, and so on. In 2012, major networks like AlexNet and Deep-Q Network were built. 2016 onward, generative use cases of the deep learning also started to come up. Today, we have widely adopted deep learning for a variety of use cases, including large language models and many other types of generative models. 04:32 Lois: Hemant, what are various applications of deep learning algorithms? Hemant: Deep learning algorithms are targeted at a variety of data and applications. For data, we have images, videos, text, and audio. For images, applications can be image classification, object detection, and segmentation. For textual data, applications are to translate the text or detect a sentiment of a text. For audio, the applications can be music generation, speech to text, and so on. 05:05 Lois: It's important that we select the right deep learning algorithm based on the data and application, right? So how do we do that? Hemant: For image tasks like image classification, object detection, image segmentation, or facial recognition, CNN is a suitable architecture. For text, we have a choice of the latest transformers or LSTM or even RNN. For generative tasks like text summarization or question answering, transformers is a good choice. For generating images, text to image generation, transformers, GANs, or diffusion models are available choices. 05:45 Nikita: Let's dive a little deeper into Artificial Neural Networks. Can you tell us more about them, Hemant? Hemant: Artificial Neural Networks are inspired by the human brain. They are made up of interconnected nodes called as neurons. Nikita: And how are inputs processed by a neuron? Hemant: In ANN, we assign weights to the connection between neurons. Weighted inputs are added up. And if the sum crosses a specified threshold, the neuron is fired. And the outputs of a layer of neuron become an input to another layer. 06:16 Lois: Hemant, tell us about the building blocks of ANN so we understand this better. Hemant: So first building block is layers. We have input layer, output layer, and multiple hidden layers. The input layer and output layer are mandatory. And the hidden layers are optional. The layers consist of neurons. Neurons are computational units, which accept an input and produce an output. Weights determine the strength of connection between neurons. So the connections could be between input and a neuron, or it could be between a neuron and another neuron. Activation functions work on the weighted sum of inputs to the neuron and produce an output. Additional input to the neuron that allows a certain degree of flexibility is called as a bias. 07:05 Nikita: I think we've got the components of ANN straight but maybe you should give us an example. You mentioned this example earlier…of needing to train ANN to recognize handwritten digits from images. How would we go about that? Hemant: For that, we have to collect a large number of digit images, and we need to train ANN using these images. So, in this case, the images consist of 28 by 28 pixels, which act as input layer. For the output, we have 10 neurons which represent digits 0 to 9. And we have multiple hidden layers. So, for example, we have two hidden layers which are consisting of 16 neurons each. The hidden layers are responsible for capturing the internal representation of the raw images. And the output layer is responsible for producing the desired outcomes. So, in this case, the desired outcome is the prediction of whether the digit is 0 or 1 or up to digit 9. So how do we train this particular ANN? So the first thing we use is the backpropagation algorithm. During training, we show an image to the ANN. Let's say it is an image of digit 2. So we expect output neuron for digit 2 to fire. But in real, let's say output neuron of a digit 6 fired. 08:28 Lois: So, then, what do we do? Hemant: We know that there is an error. So we correct an error. We adjust the weights of the connection between neurons based on a calculation, which we call as backpropagation algorithm. By showing thousands of images and adjusting the weights iteratively, ANN is able to predict correct outcomes for most of the input images. This process of adjusting weights through backpropagation is called as model training. 09:01 Do you have an idea for a new course or learning opportunity? We'd love to hear it! Visit the Oracle University Learning Community and share your thoughts with us on the Idea Incubator. Your suggestion could find a place in future development projects! Visit mylearn.oracle.com to get started. 09:22 Nikita: Welcome back! Let's move on to CNN. Hemant, what is a Convolutional Neural Network? Hemant: CNN is a type of deep learning model specifically designed for processing and analyzing grid-like data, such as images and videos. In the ANN, the input image is converted to a single dimensional array and given as an input to the network. But that does not work well with the image data because image data is inherently two dimensional. CNN works better with the two dimensional data. The role of the CNN is to reduce the images into a form, which is easier to process and without losing features, which are critical for getting a good prediction. 10:10 Lois: A CNN has different layers, right? Could you tell us a bit about them? Hemant: The first one is input layer. Input layer is followed by feature extraction layers, which is a combination and repetition of convolutional layer with ReLu activation and a pooling layer. And this is followed by a classification layer. These are the fully connected output layers, where the classification occurs as output classes. The class with the highest probability is the predicted class. And finally, we have the dropout layer. This layer is a regularization technique used to prevent overfitting in the network. 10:51 Nikita: And what are the top applications of CNN? Hemant: One of the most widely used applications of CNNs is image classification. For example, classifying whether an image contains a specific object, say cat or a dog. CNNs are also used for object detection tasks. The goal here is to draw bounding boxes around objects in an image. CNNs can perform pixel-level segmentation, where each pixel in the image is labeled to represent different objects or regions. CNNs are employed for face recognition tasks as well, identifying and verifying individuals based on facial features. CNNs are widely used in medical image analysis, helping with tasks like tumor detection, diagnosis, and classification of various medical conditions. CNNs play an important role in the development of self-driving cars, helping them to recognize and understand the road traffic signs, pedestrians, and other vehicles. 12:02 Nikita: Hemant, let's talk about sequence models. What are they and what are they used for? Hemant: Sequence models are used to solve problems, where the input data is in the form of sequences. The sequences are ordered lists of data points or events. The goal in sequence models is to find patterns and dependencies within the data and make predictions, classifications, or even generate new sequences. 12:31 Lois: Can you give us some examples of sequence models? Hemant: Some common examples of the sequence models are in natural language processing, deep learning models are used for tasks, such as machine translation, sentiment analysis, or text generation. In speech recognition, deep learning models are used to convert a recorded audio into text. Deep learning models can generate new music or create original compositions. Even sequences of hand gestures are interpreted by deep learning models for applications like sign language recognition. In fields like finance or weather prediction, time series data is used to predict future values. 13:15 Nikita: Which deep learning models can be used to work with sequence data? Hemant: Recurrent Neural Networks, abbreviated as RNNs, are a class of neural network architectures specifically designed to handle sequential data. Unlike traditional feedforward neural network, RNNs have a feedback loop that allows information to persist across different timesteps. The key features of RNNs is their ability to maintain an internal state often referred to as a hidden state or memory, which is updated as the network processes each element in the input sequence. The hidden state is used as input to the network for the next time step, allowing the model to capture dependencies and patterns in the data that are spread across time. 14:07 Nikita: Are there various types of RNNs? Hemant: There are different types of RNN architectures based on application. One of them is one to one. This is like feed forward neural network and is not suited for sequential data. A one to many model produces multiple output values for one input value. Music generation or sequence generation are some applications using this architecture. A many to one model produces one output value after receiving multiple input values. Example is sentiments analysis based on the review. Many to many model produces multiple output values for multiple input values. Examples are machine translation and named entity recognition. RNN does not perform well when it comes to capturing long-term dependencies. This is due to the vanishing gradients problem, which is overcome by using LSTM model. 15:11 Lois: Another acronym. What is LSTM, Hemant? Hemant: Long Short-Term memory, abbreviated as LSTM, works by using a specialized memory cell and a gating mechanism to capture long term dependencies in the sequential data. The key idea behind LSTM is to selectively remember or forget information over time, enabling the model to maintain relevant information over long sequences, which helps overcome the vanishing gradients problem. 15:45 Nikita: Can you take us, step-by-step, through the working of LSTM? Hemant: At each timestep, the LSTM takes an input vector representing the current data point in the sequence. The LSTM also receives the previous hidden state and cell state. These represent what the LSTM has remembered and forgotten up to the current point in the sequence. The core of the LSTM lies in its gating mechanisms, which include three gates: the input gate, the forget gate, and the output gate. These gates are like the filters that control the flow of information within the LSTM cell. The input gate decides what new information from the current input should be added to the memory cell. The forget gate determines what information in the current memory cell should be discarded or forgotten. The output gate regulates how much of the current memory cell should be exposed as the output of the current time step. 16:52 Lois: Thank you, Hemant, for joining us in this episode of the Oracle University Podcast. I learned so much today. If you want to learn more about deep learning, visit mylearn.oracle.com and search for the Oracle Cloud Infrastructure AI Foundations course. And remember, the AI Foundations course and certification are free. So why not get started now? Nikita: Right, Lois. In our next episode, we will discuss generative AI and language learning models. Until then, this is Nikita Abraham… Lois: And Lois Houston signing off! 17:26 That's all for this episode of the Oracle University Podcast. If you enjoyed listening, please click Subscribe to get all the latest episodes. We'd also love it if you would take a moment to rate and review us on your podcast app. See you again on the next episode of the Oracle University Podcast.
Did you know that the concept of deep learning goes way back to the 1950s? However, it is only in recent years that this technology has created a tremendous amount of buzz (and for good reason!). A subset of machine learning, deep learning is inspired by the structure of the human brain, making it fascinating to learn about. In this episode, Lois Houston and Nikita Abraham interview Senior Principal OCI Instructor Hemant Gahankari about deep learning concepts, including how Convolution Neural Networks work, and help you get your deep learning basics right. Oracle MyLearn: https://mylearn.oracle.com/ Oracle University Learning Community: https://education.oracle.com/ou-community LinkedIn: https://www.linkedin.com/showcase/oracle-university/ X (formerly Twitter): https://twitter.com/Oracle_Edu Special thanks to Arijit Ghosh, David Wright, Himanshu Raj, and the OU Studio Team for helping us create this episode. -------------------------------------------------------- Episode Transcript: 00:00 Welcome to the Oracle University Podcast, the first stop on your cloud journey. During this series of informative podcasts, we'll bring you foundational training on the most popular Oracle technologies. Let's get started! 00:26 Lois: Hello and welcome to the Oracle University Podcast. I'm Lois Houston, Director of Innovation Programs with Oracle University, and with me is Nikita Abraham, Principal Technical Editor. Nikita: Hi everyone! Last week, we covered the new MySQL HeatWave Implementation Associate certification. So do go check out that episode if it interests you. Lois: That was a really interesting discussion for sure. Today, we're going to focus on the basics of deep learning with our Senior Principal OCI Instructor, Hemant Gahankari. 00:58 Nikita: Hi Hemant! Thanks for being with us today. So, to get started, what is deep learning? Hemant: Deep learning is a subset of machine learning that focuses on training Artificial Neural Networks to solve a task at hand. Say, for example, image classification. A very important quality of the ANN is that it can process raw data like pixels of an image and extract patterns from it. These patterns are treated as features to predict the outcomes. Let us say we have a set of handwritten images of digits 0 to 9. As we know, everyone writes the digits in a slightly different way. So how do we train a machine to identify a handwritten digit? For this, we use ANN. ANN accepts image pixels as inputs, extracts patterns like edges and curves and so on, and correlates these patterns to predict an outcome. That is what digit does the image has in this case. 02:04 Lois: Ok, so what you're saying is given a bunch of pixels, ANN is able to process pixel data, learn an internal representation of the data, and predict outcomes. That's so cool! So, why do we need deep learning? Hemant: We need to specify features while we train machine learning algorithm. With deep learning, features are automatically extracted from the data. Internal representation of features and their combinations is built to predict outcomes by deep learning algorithms. This may not be feasible manually. Deep learning algorithms can make use of parallel computations. For this, usually data is split into small batches and process parallelly. So these algorithms can process large amount of data in a short time to learn the features and their combinations. This leads to scalability and performance. In short, deep learning complements machine learning algorithms for complex data for which features cannot be described easily. 03:13 Nikita: What can you tell us about the origins of deep learning? Hemant: Some of the deep learning concepts like artificial neuron, perceptron, and multilayer perceptron existed as early as 1950s. One of the most important concept of using backpropagation for training ANN came in 1980s. In 1990s, convolutional neural network were also introduced for image analysis task. Starting 2000, GPUs were introduced. And 2010 onwards, GPUs became cheaper and widely available. This fueled the widespread adoption of deep learning uses like computer vision, natural language processing, speech recognition, text translation, and so on. In 2012, major networks like AlexNet and Deep-Q Network were built. 2016 onward, generative use cases of the deep learning also started to come up. Today, we have widely adopted deep learning for a variety of use cases, including large language models and many other types of generative models. 04:29 Lois: Hemant, what are various applications of deep learning algorithms? Hemant: Deep learning algorithms are targeted at a variety of data and applications. For data, we have images, videos, text, and audio. For images, applications can be image classification, object detection, and so on. For textual data, applications are to translate the text or detect a sentiment of a text. For audio, the applications can be music generation, speech to text, and so on. 05:08 Lois: It's important that we select the right deep learning algorithm based on the data and application, right? So how do we do that? Hemant: For image task like image classification, object detection, image segmentation, or facial recognition, CNN is a suitable architecture. For text, we have a choice of the latest transformers or LSTM or even RNN. For generative tasks like text summarization, question answering, transformers is a good choice. For generating images, text to image generation, transformers, GANs, or diffusion models are available choice. 05:51 Nikita: Let's dive a little deeper into Artificial Neural Networks. Can you tell us more about them, Hemant? Hemant: Artificial Neural Networks are inspired by the human brain. They are made up of interconnected nodes called as neurons. Nikita: And how are inputs processed by a neuron? Hemant: In ANN, we assign weights to the connection between neurons. Weighted inputs are added up. And if the sum crosses a specified threshold, the neuron is fired. And the outputs of a layer of neuron become an input to another layer. 06:27 Lois: Hemant, tell us about the building blocks of ANN so we understand this better. Hemant: So first, building block is layers. We have input layer, output layer, and multiple hidden layers. The input layer and output layer are mandatory. And the hidden layers are optional. The second unit is neurons. Neurons are computational units, which accept an input and produce an output. Weights determine the strength of connection between neurons. So the connection could be between input and a neuron, or it could be between a neuron and another neuron. Activation functions work on the weighted sum of inputs to a neuron and produce an output. Additional input to the neuron that allows a certain degree of flexibility is called as a bias. 07:27 Nikita: I think we've got the components of ANN straight but maybe you should give us an example. You mentioned this example earlier…of needing to train ANN to recognize handwritten digits from images. How would we go about that? Hemant: For that, we have to collect a large number of digit images, and we need to train ANN using these images. So, in this case, the images consist of 28 by 28 pixels which act as input layer. For the output, we have neurons-- 10 neurons which represent digits 0 to 9. And we have multiple hidden layers. So, in this case, we have two hidden layers which are consisting of 16 neurons each. The hidden layers are responsible for capturing the internal representation of the raw image data. And the output layer is responsible for producing the desired outcomes. So, in this case, the desired outcome is the prediction of whether the digit is 0 or 1 or up to digit 9. So how do we train this particular ANN? So the first thing we use the backpropagation algorithm. During training, we show an image to the ANN. Let us say it is an image of digit 2. So we expect output neuron for digit 2 to fire. But in real, let us say output neuron of a digit 6 fired. 09:12 Lois: So, then, what do we do? Hemant: We know that there is an error. So to correct an error, we adjust the weights of the connection between neurons based on a calculation, which we call as backpropagation algorithm. By showing thousands of images and adjusting the weights iteratively, ANN is able to predict correct outcome for most of the input images. This process of adjusting weights through backpropagation is called as model training. 09:48 Do you have an idea for a new course or learning opportunity? We'd love to hear it! Visit the Oracle University Learning Community and share your thoughts with us on the Idea Incubator. Your suggestion could find a place in future development projects! Visit mylearn.oracle.com to get started. 10:09 Nikita: Welcome back! Let's move on to CNN. Hemant, what is a Convolutional Neural Network? Hemant: CNN is a type of deep learning model specifically designed for processing and analyzing grid-like data, such as images and videos. In the ANN, the input image is converted to a single dimensional array and given as an input to the network. But that does not work well with the image data because image data is inherently two dimensional. CNN works better with two dimensional data. The role of the CNN is to reduce the image into a form, which is easier to process and without losing features, which are critical for getting a good prediction. 10:53 Lois: A CNN has different layers, right? Could you tell us a bit about them? Hemant: The first one is input layer. Input layer is followed by feature extraction layers, which is a combination and repetition of multiple feature extraction layers, including convolutional layer with ReLu activation and a pooling layer. And this is followed by a classification layer. These are the fully connected output layers, where the classification occurs as output classes. The feature extraction layers play a vital role in image classification. 11:33 Nikita: Can you explain these layers with an example? Hemant: Let us say we have a robot to inspect a house and tell us what type of a house it is. It uses many tools for this purpose. The first tool is a blueprint detector. It scans different parts of the house, like walls, floors, or windows, and looks for specific patterns or features. The second tool is a pattern highlighter. This tool marks areas detected by the blueprint detector. The next tool is a summarizer. It tries to capture the most significant features of every room. The next tool is house expert, which looks at all the highlighted patterns and features, and tries to understand the house. The next tool is a guess maker. It assigns probabilities to the different possible house types. And finally, the quality checker randomly checks different parts of the analysis to make sure that the robot doesn't rely too much on any single piece of information. 12:40 Nikita: Ok, so how are you mapping these to the feature extraction layers? Hemant: Similar to blueprint detector, we have a convolutional layer. This layer applies convolutional operations to the input image using small filters known as kernels. Each filter slides across the input image to detect specific features, such as edges, corners, or textures. Similar to pattern highlighter, we have a activation function. The activation function allows the network to learn more complex and non-linear relationships in the data. Pooling layer is similar to room summarizer. Pooling helps reduce the spatial dimensions of the feature maps generated by the convolutional layers. Similar to house expert, we have a fully connected layer, which is responsible for making final predictions or classifications based on the learned features. Softmax layer converts the output of the last fully connected layers into probability scores. The class with the highest probability is the predicted class. This is similar to the guess maker. And finally, we have the dropout layer. This layer is a regularization technique used to prevent overfitting in the network. This has the same role as that of a quality checker. 14:05 Lois: Do CNNs have any limitations that we need to be aware of? Hemant: Training CNNs on large data sets can be computationally expensive and time consuming. CNNs are susceptible to overfitting, especially when the training data is limited or imbalanced. CNNs are considered black box models making it difficult to interpret. And CNNs can be sensitive to small changes in the input leading to unstable predictions. 14:33 Nikita: And what are the top applications of CNN? Hemant: One of the most widely used applications of CNNs is image classification. For example, classifying whether an image contains a specific object, say cat or a dog. CNNs are used for object detection tasks. The goal here is to draw bounding boxes around objects in an image. CNNs can perform pixel level segmentation, where each pixel in the image is labeled to represent different objects or regions. CNNs are employed for face recognition tasks as well, identifying and verifying individuals based on facial features. CNNs are widely used in medical image analysis, helping with tasks like tumor detection, diagnosis, and classification of various medical conditions. CNNs play an important role in the development of self-driving cars, helping them to recognize and understand the road traffic signs, pedestrians, and other vehicles. And CNNs are applied in analyzing satellite images and remote sensing data for tasks, such as land cover classification and environmental monitoring. 15:50 Nikita: Hemant, let's talk about sequence models. What are they and what are they used for? Hemant: Sequence models are used to solve problems, where the input data is in the form of sequences. The sequences are ordered lists of data points or events. The goal in sequence models is to find patterns and dependencies within the data and make predictions, classifications, or even generate new sequences. 16:17 Lois: Can you give us some examples of sequence models? Hemant: Some common examples of the sequence models are in natural language processing, deep learning models are used for tasks, such as machine translation, sentiment analysis, or text generation. In speech recognition, deep learning models are used to convert a recorded audio into text. In deep learning models, can generate new music or create original compositions. Even sequences of hand gestures are interpreted by deep learning models for applications like sign language recognition. In fields like finance or weather prediction, time series data is used to predict future values. 17:03 Nikita: Which deep learning models can be used to work with sequence data? Hemant: Recurrent Neural Networks, abbreviated as RNNs, are a class of neural network architectures specifically designed to handle sequential data. Unlike traditional feedforward neural network, RNNs have a feedback loop that allows information to persist across different timesteps. The key features of RNN is their ability to maintain an internal state often referred to as a hidden state or memory, which is updated as the network processes each element in the input sequence. The hidden state is then used as input to the network for the next time step, allowing the model to capture dependencies and patterns in the data that are spread across time. 17:58 Nikita: Are there various types of RNNs? Hemant: There are different types of RNN architecture based on application. One of them is one to one. This is like feed forward neural network and is not suited for sequential data. A one to many model produces multiple output values for one input value. Music generation or sequence generation are some applications using this architecture. A many to one model produces one output value after receiving multiple input values. Example is sentiment analysis based on the review. Many to many model produces multiple output values for multiple input values. Examples are machine translation and named entity recognition. RNN does not perform that well when it comes to capturing long term dependencies. This is due to the vanishing gradients problem, which is overcome by using LSTM model. 19:07 Lois: Another acronym. What is LSTM, Hemant? Hemant: Long Short-Term memory, abbreviated as LSTM, works by using a specialized memory cell and a gating mechanisms to capture long term dependencies in the sequential data. The key idea behind LSTM is to selectively remember or forget information over time, enabling the model to maintain relevant information over long sequences, which helps overcome the vanishing gradients problem. 19:40 Nikita: Can you take us, step-by-step, through the working of LSTM? Hemant: At each timestep, the LSTM takes an input vector representing the current data point in the sequence. The LSTM also receives the previous hidden state and cell state. These represent what the LSTM has remembered and forgotten up to the current point in the sequence. The core of the LSTM lies in its gating mechanisms, which include three gates: the input gate, the forget gate, and the output gate. These gates are like the filters that control the flow of information within the LSTM cell. The input gate decides what new information from the current input should be added to the memory cell. The forget gate determines what information in the current memory cell should be discarded or forgotten. The output gate regulates how much of the current memory cell should be exposed as the output of the current time step. Using the information from the input gate and forget gate, the LSTM updates its cell state. The LSTM then uses the output gate to produce the current hidden state, which becomes the output of the LSTM for the next time step. 21:12 Lois: Thank you, Hemant, for joining us in this episode of the Oracle University Podcast. I learned so much today. If you want to learn more about deep learning, visit mylearn.oracle.com and search for the Oracle Cloud Infrastructure AI Foundations course. And remember, the AI Foundations course and certification are free. So why not get started now? Nikita: Right, Lois. In our next episode, we will discuss generative AI and language learning models. Until then, this is Nikita Abraham… Lois: And Lois Houston signing off! 21:45 That's all for this episode of the Oracle University Podcast. If you enjoyed listening, please click Subscribe to get all the latest episodes. We'd also love it if you would take a moment to rate and review us on your podcast app. See you again on the next episode of the Oracle University Podcast.
John Joseph Hopfield (born July 15, 1933) is an American scientist most widely known for his invention of an associative neural network in 1982. It is now more commonly known as the Hopfield network. Hopfield was born in 1933 to Polish physicist John Joseph Hopfield and physicist Helen Hopfield. Helen was the older Hopfield's second wife. He is the sixth of Hopfield's children and has three children and six grandchildren of his own. He received his A.B. from Swarthmore College in 1954, and a Ph.D. in physics from Cornell University in 1958 (supervised by Albert Overhauser). He spent two years in the theory group at Bell Laboratories, and subsequently was a faculty member at University of California, Berkeley (physics), Princeton University (physics), California Institute of Technology (chemistry and biology) and again at Princeton, where he is the Howard A. Prior Professor of Molecular Biology, emeritus. For 35 years, he also continued a strong connection with Bell Laboratories. In 1986 he was a co-founder of the Computation and Neural Systems PhD program at Caltech. His most influential papers have been "The Contribution of Excitons to the Complex Dielectric Constant of Crystals" (1958), describing the polariton; "Electron transfer between biological molecules by thermally activated tunneling" (1974), describing the quantum mechanics of long-range electron transfers; "Kinetic Proofreading: a New Mechanism for Reducing Errors in Biosynthetic Processes Requiring High Specificity" (1974); "Neural networks and physical systems with emergent collective computational abilities" (1982) (known as the Hopfield Network) and, with D. W. Tank, "Neural computation of decisions in optimization problems" (1985). His current research and recent papers are chiefly focused on the ways in which action potential timing and synchrony can be used in neurobiological computation. Audio source Buy me a coffee John Hopfield - Wikipedia Internet Archive CHAPTERS: (00:00) Intro (06:00) Artificial Neural Networks and Speech Processing (01:04:19) Q&A --- Support this podcast: https://podcasters.spotify.com/pod/show/theunadulteratedintellect/support
Join Hugh Ross and Jeff Zweerink as they discuss new discoveries taking place at the frontiers of science that have theological and philosophical implications, including the reality of God's existence. JWST Galaxies Explained The James Webb Space Telescope (JWST) has revealed that early galaxies have much brighter ultraviolet luminosities than many big bang creation models predicted. Do such data challenge the creation view? Further research suggests not. Using a computer simulation, astronomers have found that the standard big bang creation models can still accommodate the new data from JWST. Their conclusions remain consistent with the findings reported in the Stars, Cells, and God episode #79 on the “Source of Heavy Elements”, aired on November 29, 2023. RESOURCES: Bursty Star Formation Naturally Explains the Abundance of Bright Galaxies at Cosmic Dawn Dilution of Chemical Enrichment in Galaxies 600 Myr after the Big Bang AI Sees Differently than Us As AIs (artificial intelligence) mimic more and more human behavior, the question continues to arise of whether AI is truly intelligent or not. One way to assess the data is to understand whether the AI does things differently than a human. In the arena of image and audio recognition, AIs have advanced tremendously, but there are some noticeable discrepancies between AI and human categorization. Research into one type of discrepancy shows that humans and AIs really do see the world differently—and those differences highlight important defining features of humanity. RESOURCES: Model Metamers Reveal Divergent Invariances between Biological and Artificial Neural Networks
Neuroscientist David Eagleman joins the show to talk about lighthearted topics ranging from the nature of consciousness to the intersection of technology and the grey matter that lives in our skulls.See omnystudio.com/listener for privacy information.
Professor Peter Andras is the Dean of the School of Computing, Engineering & the Built Environment. Previously, Peter was the Head of the School of Computing and Mathematics (2017 – 2021) and Professor of Computer Science and Informatics at Keele University from 2014 – 2021. Prior to this he worked at Newcastle University in the School of Computing (2002 – 2014) and the Department of Psychology (2000 – 2002). He has a PhD in Mathematical Analysis of Artificial Neural Networks (2000), MSc in Artificial Intelligence (1996) and BSc in Computer Science (1995), all from the Babes-Bolyai University, Romania. Peter's research interests span a range of subjects including artificial intelligence, machine learning, complex systems, agent-based modelling, software engineering, systems theory, neuroscience, modelling and analysis of biological and social systems. He has worked on many research projects, mostly in collaboration with other researchers in computer science, psychology, chemistry, electronic engineering, mathematics, economics and other areas. His research projects have received around £2.5 million funding, his papers have been cited by over 2,400 times and his h-index is 25 according to Google Scholar. Peter has extensive experience of working with industry, including several KTP projects and three university spin-out companies, one of which is on the London Stock Exchange since 2007 – eTherapeutics plc. Peter is member of the Board of Governors of the International Neural Network Society (INNS), Fellow of the Royal Society of Biology, Senior Member of the Institute of Electrical and Electronics Engineers (IEEE) and member of the UK Computing Research Committee (UKCRC), IEEE Computer Society, Society for Artificial Intelligence and Simulation of Behaviour (AISB), International Society for Artificial Life (ISAL) and the Society for Neuroscience (SfN). Peter serves on the EPSRC Peer Review College, the Royal Society International Exchanges Panel and the Royal Society APEX Awards Review College. He is also regularly serving as review panel member and project assessor for EU funding agencies. Outside academia, Peter has an interest in politics and community affairs. He served as local councillor in Newcastle upon Tyne, parish councillor in Keele and stood in general elections for the Parliament. He has experience of working with and leading community organisations and leading a not-for-profit regional development consultancy and project management organisation. Ref: https://www.napier.ac.uk/people/peter-andras
Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2023.07.26.550361v1?rss=1 Authors: Kossowsky Lev, H., Nisky, I. Abstract: Applying artificial skin stretch with force feedback increases perceived stiffness and affects grip force. We explored if participants' perceptual responses in a stiffness discrimination task could be predicted solely from their action signals using models and artificial neural networks. Successful prediction could indicate a relation between participants' perception and action. We found that the skin stretch perceptual augmentation could be predicted to an extent from action signals alone. We predicted the general trend of increased predicted augmentation for increased real augmentation, and average augmentation effect across participants, but not the precise effect sizes of individual participants. This indicates some relation between participants' perceptual reports and action signals, enabling the partial prediction. Furthermore, of the action signals examined, grip force was necessary for predicting the augmentation effect, and a motion signal (e.g., position) was needed for predicting human-like perception, shedding light on what information may be present in the different signals. Copy rights belong to original authors. Visit the link for more info Podcast created by Paper Player, LLC
E309– Inner Voice – a Heartfelt Chat with Dr. Foojan. In this episode, Dr. Foojan Zeine chats with Dr. Marcello (Giuseppe) Tanca. He has a Ph.D. In Neuroscience and is a Clinical Psychologist. He joins us from the Italian island of Sardinia, where he currently lives and works in his private practice performing: Psychodiagnosis, Psychotherapy, and Neuroscientific research. He was a visiting researcher at Stanford University, before going back to Italy to teach “Neuroscience and Psychodiagnosis” at the Psychotherapy Specialization School in Cagliari-Italy. As a researcher, he studies, in particular, the relationship between inflammatory processes and psychological/psychiatric symptoms. With research groups in the biomedical field that use cutting-edge approaches (such as Metabolomics and Artificial Neural Networks), he published research in international scientific journals, focused on “PANS”: "Pediatric Acute-Onset Neuropsychiatric Syndrome". PANS is a syndrome supported by the presence of an immune pathogenetic, based on dysregulation of the immune system, with its inflammatory correlates. Today we will be talking about his latest book, written in Italian, "Neuro-Inflammation and Dysfunction of Mental Processes - an introduction to the Importance of a new study perspective in Neuroscience". You may contact him at marcellotanca@hotmail.it Check out my website: www.FoojanZeine.com. Remember to Subscribe, Listen, Review, and Share! Find me on these sites: *iTunes (https://itunes.apple.com/us/podcast/i...) *Google Play (https://play.google.com/music/m/Inpl5...) *Stitcher (https://www.stitcher.com/s?fid=185544...) *YouTube (https://www.youtube.com/DrFoojanZeine ) Platforms to Like and Follow: *Facebook (https://www.facebook.com/DrFoojanZeine/) *Instagram (https://www.instagram.com/Dr.FoojanZe...) *Twitter (https://www.twitter.com/DrZeine/) *LinkedIn (https://www.linkedin.com/in/DrFoojanZ...)
The recent developments in AI are quite impressive. If someone had told me a couple years ago about the capabilities of something like ChatGPT I wouldn't have believed them. AI certainly has enormous practical benefit. But since artificial neural networks were inspired by biological neural networks they can also be useful models for them. In this episode I share some recent studies investigating the behavior of the brain using AI models and evaluating their possible underlying computational similarities.
Dr. Geoffrey Hinton recently retired from Google, saying that he wanted to be able to speak freely about his concerns regarding artificial intelligence without having to consider the impact to his employer. So what is the Godfather of AI worried about? See omnystudio.com/listener for privacy information.
AI Today Podcast: Artificial Intelligence Insights, Experts, and Opinion
If we can replicate neurons and how they are connected, can we replicate the behavior of our brains? In this episode of the AI Today podcast hosts Kathleen Walch and Ron Schmelzer define the terms (Artificial) Neural Networks, Node, and layer, and explain how they relate to AI and why it's important to know about them. Continue reading AI Today Podcast: AI Glossary Series – (Artificial) Neural Networks, Node (Neuron), Layer at AI & Data Today.
"Introduction to Deep Learning" - A comprehensive guide to the fundamental concepts of deep learning, including artificial neural networks, activation functions, loss functions, and deep learning architectures like feedforward networks, recurrent networks, and convolutional networks. Explore the applications of deep learning in various industries and discover recommended resources for further learning. Get a solid foundation in deep learning with this informative episode!Support the Show.Keep AI insights flowing – become a supporter of the show!Click the link for details
Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2023.02.17.528969v1?rss=1 Authors: Codol, O., Michaels, J. A., Kashefi, M., Pruszynski, J. A., Gribble, P. L. Abstract: Artificial neural networks (ANNs) are a powerful class of computational models for unravelling neural mechanisms of brain function. However, for neural control of movement, they currently must be integrated with software simulating biomechanical effectors, leading to limiting impracticalities: (1) researchers must rely on two different platforms and (2) biomechanical effectors are not generally differentiable, constraining researchers to reinforcement learning algorithms despite the existence and potential biological relevance of faster training methods. To address these limitations, we developed MotorNet, an open-source Python toolbox for creating arbitrarily complex, differentiable, and biomechanically realistic effectors that can be trained on user-defined motor tasks using ANNs. MotorNet is designed to meet several goals: ease of installation, ease of use, a high-level user-friendly API, and a modular architecture to allow for flexibility in model building. MotorNet requires no dependencies outside Python, making it easy to get started with. For instance, it allows training ANNs on typically used motor control models such as a two joint, six muscle, planar arm within minutes on a typical desktop computer. MotorNet is built on TensorFlow and therefore can implement any network architecture that is possible using the TensorFlow framework. Consequently, it will immediately benefit from advances in artificial intelligence through TensorFlow updates. Finally, it is open source, enabling users to create and share their own improvements, such as new effector and network architectures or custom task designs. MotorNet's focus on higher order model and task design will alleviate overhead cost to initiate computational projects for new researchers by providing a standalone, ready-to-go framework, and speed up efforts of established computational teams by enabling a focus on concepts and ideas over implementation. Copy rights belong to original authors. Visit the link for more info Podcast created by Paper Player, LLC
The brain is a marvelous organ still not understood. Artificial neural networks are supposed to be a simulation of the human brain. But comparing the brain to an artificial neural network is like comparing the human heart to a pump handle. Dr. Andrew Knox and Dr. Robert J. Marks discuss the brain, aging, and neurology. Additional Resources Source
Her har vi en algoritme som med forsterkningslæring lærer seg når det er lurt å lade batteriene og når det er lurt å forbruke strøm, slik at vi får energi til lavest mulig pris. Artikkel: Augmented Random Search with Artificial Neural Networks for energy cost optimization with battery control, Prøv selv: https://www.sciencedirect.com/science/article/pii/S0959652622042482
6.28 demystifies the MLB playoffs format (0:36), checks some Fantasy topline numbers (3:44), presents Stats 101 Lesson 5.1: More on Artificial Neural Networks (ANN) (7:04), and reviews Spencer Strider (25:51).
Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2022.09.30.510374v1?rss=1 Authors: Schmidgall, S., Schuman, C., Parsa, M. Abstract: Grand efforts in neuroscience are working toward mapping the connectomes of many new species, including the near completion of the Drosophila melanogaster. It is important to ask whether these models could benefit artificial intelligence. In this work we ask two fundamental questions: (1) where and when biological connectomes can provide use in machine learning, (2) which design principles are necessary for extracting a good representation of the connectome. Toward this end, we translate the motor circuit of the C. Elegans nematode into artificial neural networks at varying levels of biophysical realism and evaluate the outcome of training these networks on motor and non-motor behavioral tasks. We demonstrate that biophysical realism need not be upheld to attain the advantages of using biological circuits. We also establish that, even if the exact wiring diagram is not retained, the architectural statistics provide a valuable prior. Finally, we show that while the C. Elegans locomotion circuit provides a powerful inductive bias on locomotion problems, its structure may hinder performance on tasks unrelated to locomotion such as visual classification problems. Copy rights belong to original authors. Visit the link for more info Podcast created by PaperPlayer
6.27 unties a few MLB fantasy storylines (0:39), checks some Fantasy topline numbers (2:47), presents Stats 101 Lesson 5: Advanced Inferential Statistics: Artificial Neural Networks (ANN) (4:10), and reviews Kevin Gausman (23:02).
An artificial neural network is a computer algorithm somewhat inspired by our brains. Superficially, our brain is a network of neurons connected with each other and communicating via electrical impulses. Artificial intelligence experts implemented a similar concept purely in software. An artificial neuron is basically a function that takes a set of inputs and has an output. Just like the biological one. By connecting hundreds of such neurons in a network, we can observe quite intelligent behaviours. For example, artificial neural networks can recognize what's in the image. Or quite the opposite - generate images from text. Read more: https://nurkiewicz.com/87 Get the new episode straight to your mailbox: https://nurkiewicz.com/newsletter
Sometimes applications crash. Some other times applications crash because memory is exhausted. Such issues exist because of bugs in the code, or heavy memory usage for reasons that were not expected during design and implementation. Can we use machine learning to predict and eventually detect out of memory kills from the operating system? Apparently, the Netflix app many of us use on a daily basis leverage ML and time series analysis to prevent OOM-kills. Enjoy the show! Our Sponsors Explore the Complex World of Regulations. Compliance can be overwhelming. Multiple frameworks. Overlapping requirements. Let Arctic Wolf be your guide. Check it out at https://arcticwolf.com/datascience Amethix works to create and maximize the impact of the world's leading corporations and startups, so they can create a better future for everyone they serve. We provide solutions in AI/ML, Fintech, Healthcare/RWE, and Predictive maintenance. Transcript 1 00:00:04,150 --> 00:00:09,034 And here we are again with the season four of the Data Science at Home podcast. 2 00:00:09,142 --> 00:00:19,170 This time we have something for you if you want to help us shape the data science leaders of the future, we have created the the Data Science at Home's Ambassador program. 3 00:00:19,340 --> 00:00:28,378 Ambassadors are volunteers who are passionate about data science and want to give back to our growing community of data science professionals and enthusiasts. 4 00:00:28,534 --> 00:00:37,558 You will be instrumental in helping us achieve our goal of raising awareness about the critical role of data science in cutting edge technologies. 5 00:00:37,714 --> 00:00:45,740 If you want to learn more about this program, visit the Ambassadors page on our website@datascienceathome.com. 6 00:00:46,430 --> 00:00:49,234 Welcome back to another episode of Data Science at Home podcast. 7 00:00:49,282 --> 00:00:55,426 I'm Francesco Podcasting from the Regular Office of Amethyx Technologies, based in Belgium. 8 00:00:55,618 --> 00:01:02,914 In this episode, I want to speak about a machine learning problem that has been formulated at Netflix. 9 00:01:03,022 --> 00:01:22,038 And for the record, Netflix is not sponsoring this episode, though I still believe that this problem is a very well known problem, a very common one across factors, which is how to predict out of memory kill in an application and formulate this problem as a machine learning problem. 10 00:01:22,184 --> 00:01:39,142 So this is something that, as I said, is very interesting, not just because of Netflix, but because it allows me to explain a few points that, as I said, are kind of invariance across sectors. 11 00:01:39,226 --> 00:01:56,218 Regardless of your application, is a video streaming application or any other communication type of application, or a fintech application, or energy, or whatever, this memory kill, out of memory kill still occurs. 12 00:01:56,314 --> 00:02:05,622 And what is an out of memory kill? Well, it's essentially the extreme event in which the machine doesn't have any more memory left. 13 00:02:05,756 --> 00:02:16,678 And so usually the operating system can start eventually swapping, which means using the SSD or the hard drive as a source of memory. 14 00:02:16,834 --> 00:02:19,100 But that, of course, will slow down a lot. 15 00:02:19,430 --> 00:02:45,210 And eventually when there is a bug or a memory leak, or if there are other applications running on the same machine, of course there is some kind of limiting factor that essentially kills the application, something that occurs from the operating system most of the time that kills the application in order to prevent the application from monopolizing the entire machine, the hardware of the machine. 16 00:02:45,710 --> 00:02:48,500 And so this is a very important problem. 17 00:02:49,070 --> 00:03:03,306 Also, it is important to have an episode about this because there are some strategies that I've used at Netflix that are pretty much in line with what I believe machine learning should be about. 18 00:03:03,368 --> 00:03:25,062 And usually people would go for the fancy solution there like this extremely accurate predictors or machine learning models, but you should have a massive number of parameters and that try to figure out whatever is happening on that machine that is running that application. 19 00:03:25,256 --> 00:03:29,466 While the solution at Netflix is pretty straightforward, it's pretty simple. 20 00:03:29,588 --> 00:03:33,654 And so one would say then why making an episode after this? Well. 21 00:03:33,692 --> 00:03:45,730 Because I think that we need more sobriety when it comes to machine learning and I believe we still need to spend a lot of time thinking about what data to collect. 22 00:03:45,910 --> 00:03:59,730 Reasoning about what is the problem at hand and what is the data that can actually tickle the particular machine learning model and then of course move to the actual prediction that is the actual model. 23 00:03:59,900 --> 00:04:15,910 That most of the time it doesn't need to be one of these super fancy things that you see on the news around chatbots or autonomous gaming agent or drivers and so on and so forth. 24 00:04:16,030 --> 00:04:28,518 So there are essentially two data sets that the people at Netflix focus on which are consistently different, dramatically different in fact. 25 00:04:28,604 --> 00:04:45,570 These are data about device characteristics and capabilities and of course data that are collected at Runtime and that give you a picture of what's going on in the memory of the device, right? So that's the so called runtime memory data and out of memory kills. 26 00:04:45,950 --> 00:05:03,562 So the first type of data is I would consider it very static because it considers for example, the device type ID, the version of the software development kit that application is running, cache capacities, buffer capacities and so on and so forth. 27 00:05:03,646 --> 00:05:11,190 So it's something that most of the time doesn't change across sessions and so that's why it's considered static. 28 00:05:12,050 --> 00:05:18,430 In contrast, the other type of data, the Runtime memory data, as the name says it's runtime. 29 00:05:18,490 --> 00:05:24,190 So it varies across the life of the session it's collected at Runtime. 30 00:05:24,250 --> 00:05:25,938 So it's very dynamic data. 31 00:05:26,084 --> 00:05:36,298 And example of these records are for example, profile, movie details, playback information, current memory usage, et cetera, et cetera. 32 00:05:36,334 --> 00:05:56,086 So this is the data that actually moves and moves in the sense that it changes depending on how the user is actually using the Netflix application, what movie or what profile description, what movie detail has been loaded for that particular movie and so on and so forth. 33 00:05:56,218 --> 00:06:15,094 So one thing that of course the first difficulty of the first challenge that the people at Netflix had to deal with was how would you combine these two things, very static and usually small tables versus very dynamic and usually large tables or views. 34 00:06:15,142 --> 00:06:36,702 Well, there is some sort of join on key that is performed by the people at Netflix in order to put together these different data resolutions, right, which is data of the same phenomenon but from different sources and with different carrying very different signals in there. 35 00:06:36,896 --> 00:06:48,620 So the device capabilities is captured usually by the static data and of course the other data, the Runtime memory and out of memory kill data. 36 00:06:48,950 --> 00:07:04,162 These are also, as I said, the data that will describe pretty accurately how is the user using that particular application on that particular hardware. 37 00:07:04,306 --> 00:07:17,566 Now of course, when it comes to data and deer, there is nothing new that people at Netflix have introduced dealing with missing data for example, or incorporating knowledge of devices. 38 00:07:17,698 --> 00:07:26,062 It's all stuff that it's part of the so called data cleaning and data collection strategy, right? Or data preparation. 39 00:07:26,146 --> 00:07:40,782 That is, whatever you're going to do in order to make that data or a combination of these data sources, let's say, compatible with the way your machine learning model will understand or will read that data. 40 00:07:40,916 --> 00:07:58,638 So if you think of a big data platform, the first step, the first challenge you have to deal, you have to deal with is how can I, first of all, collect the right amount of information, the right data, but also how to transform this data for my particular big data platform. 41 00:07:58,784 --> 00:08:12,798 And that's something that, again, nothing new, nothing fancy, just basics, what we have been used to, what we are used to seeing now for the last decade or more, that's exactly what they do. 42 00:08:12,944 --> 00:08:15,222 And now let me tell you something important. 43 00:08:15,416 --> 00:08:17,278 Cybercriminals are evolving. 44 00:08:17,374 --> 00:08:22,446 Their techniques and tactics are more advanced, intricate and dangerous than ever before. 45 00:08:22,628 --> 00:08:30,630 Industries and governments around the world are fighting back on dealing new regulations meant to better protect data against this rising threat. 46 00:08:30,950 --> 00:08:39,262 Today, the world of cybersecurity compliance is a complex one, and understanding the requirements your organization must adhere to can be a daunting task. 47 00:08:39,406 --> 00:08:42,178 But not when the pack has your best architect. 48 00:08:42,214 --> 00:08:53,840 Wolf, the leader in security operations, is on a mission to end cyber risk by giving organizations the protection, information and confidence they need to protect their people, technology and data. 49 00:08:54,170 --> 00:09:02,734 The new interactive compliance portal helps you discover the regulations in your region and industry and start the journey towards achieving and maintaining compliance. 50 00:09:02,902 --> 00:09:07,542 Visit Arcticwolves.com DataScience to take your first step. 51 00:09:07,676 --> 00:09:11,490 That's arcticwolf.com DataScience. 52 00:09:12,050 --> 00:09:18,378 I think that the most important part, though, I think are actually equally important. 53 00:09:18,464 --> 00:09:26,854 But the way they treat runtime memory data and out of memory kill data is by using sliding windows. 54 00:09:26,962 --> 00:09:38,718 So that's something that is really worth mentioning, because the way you would frame this problem is something is happening at some point in time and I have to kind of predict that event. 55 00:09:38,864 --> 00:09:49,326 That is usually an outlier in the sense that these events are quite rare, fortunately, because Netflix would not be as usable as we believe it is. 56 00:09:49,448 --> 00:10:04,110 So you would like to predict these weird events by looking at a historical view or an historical amount of records that you have before this particular event, which is the kill of the application. 57 00:10:04,220 --> 00:10:12,870 So the concept of the sliding window, the sliding window approach is something that comes as the most natural thing anyone would do. 58 00:10:13,040 --> 00:10:18,366 And that's exactly what the researchers and Netflix have done. 59 00:10:18,488 --> 00:10:25,494 So unexpectedly, in my opinion, they treated this problem as a time series, which is exactly what it is. 60 00:10:25,652 --> 00:10:26,190 Now. 61 00:10:26,300 --> 00:10:26,754 They. 62 00:10:26,852 --> 00:10:27,330 Of course. 63 00:10:27,380 --> 00:10:31,426 Use this sliding window with a different horizon. 64 00:10:31,558 --> 00:10:32,190 Five minutes. 65 00:10:32,240 --> 00:10:32,838 Four minutes. 66 00:10:32,924 --> 00:10:33,702 Two minutes. 67 00:10:33,836 --> 00:10:36,366 As close as possible to the event. 68 00:10:36,548 --> 00:10:38,886 Because maybe there are some. 69 00:10:39,008 --> 00:10:39,762 Let's say. 70 00:10:39,896 --> 00:10:45,678 Other dynamics that can raise when you are very close to the event or when you are very far from it. 71 00:10:45,704 --> 00:10:50,166 Like five minutes far from the out of memory kill. 72 00:10:50,348 --> 00:10:51,858 Might have some other. 73 00:10:51,944 --> 00:10:52,410 Let's say. 74 00:10:52,460 --> 00:10:55,986 Diagrams or shapes in the data. 75 00:10:56,168 --> 00:11:11,310 So for example, you might have a certain number of allocations that keep growing and growing, but eventually they grow with a certain curve or a certain rate that you can measure when you are five to ten minutes far from the out of memory kill. 76 00:11:11,420 --> 00:11:16,566 When you are two minutes far from the out of memory kill, probably this trend will change. 77 00:11:16,688 --> 00:11:30,800 And so probably what you would expect is that the memory is already half or more saturated and therefore, for example, the operating system starts swapping or other things are happening that you are going to measure in this. 78 00:11:31,550 --> 00:11:39,730 And that would give you a much better picture of what's going on in the, let's say, closest neighborhood of that event, the time window. 79 00:11:39,790 --> 00:11:51,042 The sliding window and time window approach is definitely worth mentioning because this is something that you can apply if you think pretty much anywhere right now. 80 00:11:51,116 --> 00:11:52,050 What they did. 81 00:11:52,160 --> 00:12:04,146 In addition to having a time window, a sliding window, they also assign different levels to memory readings that are closer to the out of memory kill. 82 00:12:04,208 --> 00:12:10,062 And usually these levels are higher and higher as we get closer and closer to the out of memory kill. 83 00:12:10,136 --> 00:12:15,402 So this means that, for example, we would have, for a five minute window, we would have a level one. 84 00:12:15,596 --> 00:12:22,230 Five minute means five minutes far from the out of memory kill, four minutes would be a level two. 85 00:12:22,280 --> 00:12:37,234 Three minutes it's much closer would be a level three, two minutes would be a level four, which means like kind of the severity of the event as we get closer and closer to the actual event when the application is actually killed. 86 00:12:37,342 --> 00:12:51,474 So by looking at this approach, nothing new there, even, I would say not even a seasoned data scientist would have understood that using a sliding window is the way to go. 87 00:12:51,632 --> 00:12:55,482 I'm not saying that Netflix engineers are not seasoned enough. 88 00:12:55,556 --> 00:13:04,350 Actually they do a great job every day to keep giving us video streaming platforms that actually never fail or almost never fail. 89 00:13:04,910 --> 00:13:07,460 So spot on there, guys, good job. 90 00:13:07,850 --> 00:13:27,738 But looking at this sliding window approach, the direct consequence of this is that they can plot, they can do some sort of graphical analysis of the out of memory kills versus the memory usage that can give the reader or the data scientist a very nice picture of what's going on there. 91 00:13:27,824 --> 00:13:39,330 And so you would have, for example, and I would definitely report some of the pictures, some of the diagrams and graphs in the show notes of this episode on the official website datascienceaton.com. 92 00:13:39,500 --> 00:13:48,238 But essentially what you can see there is that there might be premature peaks at, let's say, a lower memory reading. 93 00:13:48,334 --> 00:14:08,958 And usually these are some kind of false positives or anomalies that should not be there, then it's possible to set a threshold where the threshold to start lowering the memory usage because after that threshold something nasty can happen and usually happens according to your data. 94 00:14:09,104 --> 00:14:18,740 And then of course there is another graph about the Gaussian distribution or in fact no sharp peak at all. 95 00:14:19,250 --> 00:14:21,898 That is like kills or out of memory. 96 00:14:21,934 --> 00:14:33,754 Kills are more or less distributed in a normalized fashion and then of course there are the genuine peaks that indicate that kills near, let's say, the threshold. 97 00:14:33,802 --> 00:14:38,758 And so usually you would see that after that particular threshold of memory usage. 98 00:14:38,914 --> 00:14:42,142 You see most of the out of memory kills. 99 00:14:42,226 --> 00:14:45,570 Which makes sense because given a particular device. 100 00:14:45,890 --> 00:14:48,298 Which means certain amount of memories. 101 00:14:48,394 --> 00:14:50,338 Certain memory characteristics. 102 00:14:50,494 --> 00:14:53,074 Certain version of the SDK and so on and so forth. 103 00:14:53,182 --> 00:14:53,814 You can say. 104 00:14:53,852 --> 00:14:54,090 Okay. 105 00:14:54,140 --> 00:15:10,510 Well for this device type I have this memory memory usage threshold and after this I see that I have a relatively high number of out of memory kills immediately after this threshold. 106 00:15:10,570 --> 00:15:18,150 And this means that probably that is the threshold you would like to consider as the critical threshold you should never or almost never cross. 107 00:15:18,710 --> 00:15:38,758 So once you have this picture in front of you, you can start thinking of implementing some mechanisms that can monitor the memory usage and of course kind of preemptively dialocate things or keep that memory threshold as low as possible with respect to the critical threshold. 108 00:15:38,794 --> 00:15:53,446 So you can start implementing some logic that prevents the application from being killed by the operating system so that you would in fact reduce the rate of out of memory kills overall. 109 00:15:53,578 --> 00:16:11,410 Now, as always and as also the engineers state in their blog post, in the technical post, they say well, it's much more important for us to predict with a certain amount of false positive rather than false negatives. 110 00:16:11,590 --> 00:16:18,718 False negatives means missing an out of memory kill that actually occurred but got not predicted. 111 00:16:18,874 --> 00:16:40,462 If you are a regular listener of this podcast, that statement should resonate with you because this is exactly what happens, for example in healthcare applications, which means that doctors or algorithms that operate in healthcare would definitely prefer to have a bit more false positives rather than more false negatives. 112 00:16:40,486 --> 00:16:54,800 Because missing that someone is sick means that you are not providing a cure and you're just sending the patient home when he or she is sick, right? That's the false positive, it's the mess. 113 00:16:55,130 --> 00:16:57,618 So that's a false negative, it's the mess. 114 00:16:57,764 --> 00:17:09,486 But having a false positive, what can go wrong with having a false positive? Well, probably you will undergo another test to make sure that the first test is confirmed or not. 115 00:17:09,608 --> 00:17:16,018 So adding a false positive in this case is relatively okay with respect to having a false negative. 116 00:17:16,054 --> 00:17:19,398 And that's exactly what happens to the Netflix application. 117 00:17:19,484 --> 00:17:32,094 Now, I don't want to say that of course Netflix application is as critical as, for example, the application that predicts a cancer or an xray or something on an xray or disorder or disease of some sort. 118 00:17:32,252 --> 00:17:48,090 But what I'm saying is that there are some analogies when it comes to machine learning and artificial intelligence and especially data science, the old school data science, there are several things that kind of are, let's say, invariant across sectors. 119 00:17:48,410 --> 00:17:56,826 And so, you know, two worlds like the media streaming or video streaming and healthcare are of course very different from each other. 120 00:17:56,888 --> 00:18:05,274 But when it comes to machine learning and data science applications, well, there are a lot of analogies there. 121 00:18:05,372 --> 00:18:06,202 And indeed. 122 00:18:06,286 --> 00:18:10,234 In terms of the models that they use at Netflix to predict. 123 00:18:10,342 --> 00:18:24,322 Once they have the sliding window data and essentially they have the ground truth of where this out of memory kill happened and what happened before to the memory of the application or the machine. 124 00:18:24,466 --> 00:18:24,774 Well. 125 00:18:24,812 --> 00:18:30,514 Then the models they use to predict these things is these events is Artificial Neural Networks. 126 00:18:30,622 --> 00:18:31,714 Xg Boost. 127 00:18:31,822 --> 00:18:36,742 Ada Boost or Adaptive Boosting Elastic Net with Softmax and so on and so forth. 128 00:18:36,766 --> 00:18:39,226 So nothing fancy. 129 00:18:39,418 --> 00:18:45,046 As you can see, Xg Boost is probably one of the most used I would have expected even random forest. 130 00:18:45,178 --> 00:18:47,120 Probably they do, they've tried that. 131 00:18:47,810 --> 00:18:58,842 But XGBoost is probably one of the most used models on kaggle competitions for a reason, because it works and it leverages a lot. 132 00:18:58,916 --> 00:19:04,880 The data preparation step, that solves already more than half of the problem. 133 00:19:05,810 --> 00:19:07,270 Thank you so much for listening. 134 00:19:07,330 --> 00:19:11,910 I also invite you, as always, to join the Discord Channel. 135 00:19:12,020 --> 00:19:15,966 You will find a link on the official website datascience@home.com. 136 00:19:16,148 --> 00:19:17,600 Speak with you next time. 137 00:19:18,350 --> 00:19:21,382 You've been listening to Data Science at home podcast. 138 00:19:21,466 --> 00:19:26,050 Be sure to subscribe on itunes, Stitcher, or Pot Bean to get new, fresh episodes. 139 00:19:26,110 --> 00:19:31,066 For more, please follow us on Instagram, Twitter and Facebook or visit our website at datascienceathome.com References https://netflixtechblog.com/formulating-out-of-memory-kill-prediction-on-the-netflix-app-as-a-machine-learning-problem-989599029109
A Google engineer was suspended after sharing a document suggesting that Google's LaMDA conversation model may be sentient. But if a machine was sentient, how could we tell? What does the Turing Test have to do with it? And can machines think? See omnystudio.com/listener for privacy information.
Hosts explain artificial neural networks, and how their function mimics the human brain. Furthermore, they go through some samples where artificial neural networks are used. In this episode we mentioned the following resources: https://www.ibm.com/cloud/learn/neural-networks https://www.sciencedirect.com/topics/earth-and-planetary-sciences/artificial-neural-network Listen to us on these channels: Pocket Casts: https://pca.st/ou3g8gao Stitcher: https://www.stitcher.com/show/664669 Listen Notes: https://www.listennotes.com/podcasts/business-of-artificial-intelligence-luca-FqNd0xHXMSl/#podcaster Podcast Addict: https://podcastaddict.com/podcast/3701044 Deezer: https://deezer.com/show/3142642 Castbox: https://castbox.fm/channel/id4661502?country=us Apple: https://podcasts.apple.com/us/podcast/artificial-intelligence-101/id1595568010 Spotify: https://open.spotify.com/show/5rRlgZl3h3SyTAY3hjWV2T Youtube: https://youtu.be/GczpFJJpbXU Do you have any AI questions you would like us to address? Leave a comment here or connect with us on Twitter: https://twitter.com/lucamarchesotti
Early in his career, IEEE fellow and retired National Science Foundation program director Paul Werbos developed the neural network training algorithm known as error backpropagation, which has been foundational to the vast majority of today’s advances in artificial intelligence. Listen in as he discusses his work in this area and other topics, including his tenure with the National Science Foundation,… Source
What can artificial neural networks teach us about our own brains? I interview Patrick Mineault, an independent scientist working at the intersection of neuroscience and deep learning. On his famous blog xcorr.net, he writes about the rapidly accelerating merger of techniques in AI and neuroscience. This field - neuroAI - aims to study how the brain works by studying artificial neural networks. Patrick did his PhD in visual neuroscience from McGill University. He has worked at Google as a scientist and then worked with Facebook to build brain-machine interfaces. Most recently, he has helped build Neuromatch Academy, an online summer school on computational neuroscience. == What we talk about == 0:00 - Introduction 1:27 - How do you define neuroAI? 4:10 - What does ‘"understanding" something even mean? 14:20 - Are there any recent cases of neuroscience learning from deep learning/AI? 23:12 - Why have the evolution-inspired methodologies not been able to match the performance of straightforward deep learning models like GPT-3? 28:33 - How can unsupervised and supervised learning methods have similar performance in modeling the brain's vision system? 36:50 - The difference between the amount of data given to process to supervised model vs unsupervised models 43:10 - Is anyone trying to model AI embedded in a 3D environment like we are? 51:15 - Do you think neuroAI can lead us to understand consciousness much more scientifically? 55:58 - Is anyone attempting to model consciousness in an artificial network? == Useful links == Patrick's blog: https://xcorr.net
AI must do what it is designed to do, but what if it doesn’t? What if AI begins behaving in bizarre and unpredictable ways? The more complex the system, the more that it can go wrong. Robert J. Marks discusses artificial general intelligence (AGI) with Justin Bui and Samuel Haug. Show Notes 00:37 | Introducing Justin Bui and Samuel Haug… Source
https://www.patreon.com/user?u=31723331 Donald Barron is the Applied Performance Analysis Lead in the School of Sport, Exercise and Health Sciences at Loughborough University. In the episode of The Know Show Podcast, he discusses his wealth of experience that he brings to the field, having worked in professional football for over ten years. He discusses his research, for example, talking about the process of scouting, scouting teams, and the potential technology has in making this fairer and more efficient. Watch for an exclusive insight into the world of football, academia, and technology in one sitting. PLEASE SUBSCRIBE TO THE CHANNEL to get the latest and most fascinating research!!! Get the latest episodes and videos on: https://theknowshow.net/ The Know Show Podcast makes the most important research accessible to everyone. Join us today and be part of the research revolution. Follow Us on Social Media: Instagram: https://www.instagram.com/theknowshow ... Twitter: https://www.instagram.com/theknowshow …
The applications of artificial neural networks are legion. Today, Robert J. Marks talks with Dr. Paul Werbos, the man who invented the method used for over four decades to train artificial neural networks. The two discuss Werbos’s mathematical journey, the error backpropagation algorithm, and the slog of “making it” in scientific academic research. Show Notes 01:19 | Introducing Dr. Paul… Source
The applications of artificial neural networks are legion. Today, Robert J. Marks talks with Dr. Paul Werbos, the man who invented the method used for over four decades to train artificial neural networks. The two discuss Werbos’s mathematical journey, the error backpropagation algorithm, and the slog of “making it” in scientific academic research. Show Notes 01:19 | Introducing Dr. Paul… Source
Evgeny Burnaev, Ph.D. Associate Professor of Center for Computational and Data-Intensive Science and Engineering (CDISE) at Skolkovo Institute of Science and Technology (Skoltech). Evgeny graduated from the Moscow Institute of Physics and Technology in 2006. After getting a Candidate of Sciences degree from the Institute for Information Transmission Problem in 2008, he stayed with the Institute as a head of the Data Analysis and Predictive Modeling Lab. Since 2007 Evgeny carried out a number of successful industrial projects with Airbus, SAFT, IHI, and Sahara Force India Formula 1 team among others. The corresponding data analysis algorithms, developed by Evgeny and his scientific group, formed a core of the algorithmic software library for metamodeling and optimization. Thanks to the developed functionality, engineers can construct fast mathematical approximations to long-running computer codes (realizing physical models) based on available data and perform design space exploration for trade-off studies. The software library passed the final Technology Readiness Level certification in Airbus. According to Airbus experts, the application of the library “provides the reduction of up to 10% of lead time and cost in several areas of the aircraft design process”. Nowadays a spin-off company Datadvance develops a Software platform for Design Space Exploration with GUI based on this algorithmic core. Evgeny's current research focuses on the development of new algorithms in machine learning and artificial intelligence such as deep networks for an approximation of physical models, generative modeling, and manifold learning, with applications to computer vision and 3D reconstruction, neurovisualization. The results are published in top computer science conferences (ICML, ICLR, NeurIPS, CVPR, ICCV, and ECCV) and journals. Evgeny Burnaev was honored with several awards for his research, including the Moscow Government Prize for Young Scientists in the category for the Transmission, Storage, Processing and Protection of Information for leading the project “The development of methods for predictive analytics for processing industrial, biomedical and financial data”, Geometry Processing Dataset Award for the work “ABC Dataset: A Big CAD Model Dataset For Geometric Deep Learning”, Symposium on Geometry Processing (2019), the Best Paper Award for the research in eSports at the IEEE Internet of People conference (2019), the Ilya Segalovich Yandex Science Prize “The best research director of postgraduate students in the field of computer sciences” (2020), the Best Paper Award for the research on modeling of point clouds and predicting properties of 3D shapes at the Int. Workshop on Artificial Neural Networks in Pattern Recognition (ANNPR) (2020). FIND EVGENY ON SOCIAL MEDIA LinkedIn | Facebook | Instagram | Twitter © Copyright 2022 Den of Rich. All rights reserved.
Evgeny Burnaev, Ph.D. Associate Professor of Center for Computational and Data-Intensive Science and Engineering (CDISE) at Skolkovo Institute of Science and Technology (Skoltech). Evgeny graduated from the Moscow Institute of Physics and Technology in 2006. After getting a Candidate of Sciences degree from the Institute for Information Transmission Problem in 2008, he stayed with the Institute as a head of the Data Analysis and Predictive Modeling Lab.Since 2007 Evgeny carried out a number of successful industrial projects with Airbus, SAFT, IHI, and Sahara Force India Formula 1 team among others. The corresponding data analysis algorithms, developed by Evgeny and his scientific group, formed a core of the algorithmic software library for metamodeling and optimization. Thanks to the developed functionality, engineers can construct fast mathematical approximations to long-running computer codes (realizing physical models) based on available data and perform design space exploration for trade-off studies. The software library passed the final Technology Readiness Level certification in Airbus. According to Airbus experts, the application of the library “provides the reduction of up to 10% of lead time and cost in several areas of the aircraft design process”. Nowadays a spin-off company Datadvance develops a Software platform for Design Space Exploration with GUI based on this algorithmic core.Evgeny's current research focuses on the development of new algorithms in machine learning and artificial intelligence such as deep networks for an approximation of physical models, generative modeling, and manifold learning, with applications to computer vision and 3D reconstruction, neurovisualization. The results are published in top computer science conferences (ICML, ICLR, NeurIPS, CVPR, ICCV, and ECCV) and journals.Evgeny Burnaev was honored with several awards for his research, including Moscow Government Prize for Young Scientists in the category for the Transmission, Storage, Processing and Protection of Information for leading the project “The development of methods for predictive analytics for processing industrial, biomedical and financial data”, Geometry Processing Dataset Award for the work “ABC Dataset: A Big CAD Model Dataset For Geometric Deep Learning”, Symposium on Geometry Processing (2019), the Best Paper Award for the research in eSports at the IEEE Internet of People conference (2019), the Ilya Segalovich Yandex Science Prize “The best research director of postgraduate students in the field of computer sciences” (2020), the Best Paper Award for the research on modeling of point clouds and predicting properties of 3D shapes at the Int. Workshop on Artificial Neural Networks in Pattern Recognition (ANNPR) (2020).FIND EVGENY ON SOCIAL MEDIALinkedIn | Facebook | Instagram | Twitter
inSonic 2020: syntheses | streaming festival [13.12.2020] Moderated by composer and AI expert Palle Dahlstedt, the second panel discussion will examine current approaches to machine learning in relation to music and sound art and will discuss them with composers, artists and scientists. Philippe Esling, Rebecca Fiebrink & Artemi-Maria Gioti
#openai #clip #microscope OpenAI does a huge investigation into the inner workings of their recent CLIP model via faceted feature visualization and finds amazing things: Some neurons in the last layer respond to distinct concepts across multiple modalities, meaning they fire for photographs, drawings, and signs depicting the same concept, even when the images are vastly distinct. Through manual examination, they identify and investigate neurons corresponding to persons, geographical regions, religions, emotions, and much more. In this video, I go through the publication and then I present my own findings from digging around in the OpenAI Microscope. OUTLINE: 0:00 - Intro & Overview 3:35 - OpenAI Microscope 7:10 - Categories of found neurons 11:10 - Person Neurons 13:00 - Donald Trump Neuron 17:15 - Emotion Neurons 22:45 - Region Neurons 26:40 - Sparse Mixture of Emotions 28:05 - Emotion Atlas 29:45 - Adversarial Typographic Attacks 31:55 - Stroop Test 33:10 - My Findings in OpenAI Microscope 33:30 - Superman Neuron 33:50 - Resting B*tchface Neuron 34:10 - Trash Bag Neuron 35:25 - God Weightlifting Neuron 36:40 - Organ Neuron 38:35 - Film Spool Neuron 39:05 - Feather Neuron 39:20 - Spartan Neuron 40:25 - Letter E Neuron 40:35 - Cleanin Neuron 40:45 - Frown Neuron 40:55 - Lion Neuron 41:05 - Fashion Model Neuron 41:20 - Baseball Neuron 41:50 - Bride Neuron 42:00 - Navy Neuron 42:30 - Hemp Neuron 43:25 - Staircase Neuron 43:45 - Disney Neuron 44:15 - Hillary Clinton Neuron 44:50 - God Neuron 45:15 - Blurry Neuron 45:35 - Arrow Neuron 45:55 - Trophy Presentation Neuron 46:10 - Receding Hairline Neuron 46:30 - Traffic Neuron 46:40 - Raised Hand Neuron 46:50 - Google Maps Neuron 47:15 - Nervous Smile Neuron 47:30 - Elvis Neuron 47:55 - The Flash Neuron 48:05 - Beard Neuron 48:15 - Kilt Neuron 48:25 - Rainy Neuron 48:35 - Electricity Neuron 48:50 - Droplets Neuron 49:00 - Escape Neuron 49:25 - King Neuron 49:35 - Country Neuron 49:45 - Overweight Men Neuron 49:55 - Wedding 50:05 - Australia Neuron 50:15 - Yawn Neuron 50:30 - Bees & Simpsons Neuron 50:40 - Mussles Neuron 50:50 - Spice Neuron 51:00 - Conclusion Paper: https://distill.pub/2021/multimodal-n... My Findings: https://www.notion.so/CLIP-OpenAI-Mic... My Video on CLIP: https://youtu.be/T9XSU0pKX2E My Video on Feature Visualizations & The OpenAI Microscope: https://youtu.be/Ok44otx90D4 Abstract: In 2005, a letter published in Nature described human neurons responding to specific people, such as Jennifer Aniston or Halle Berry. The exciting thing wasn't just that they selected for particular people, but that they did so regardless of whether they were shown photographs, drawings, or even images of the person's name. The neurons were multimodal. As the lead author would put it: "You are looking at the far end of the transformation from metric, visual shapes to conceptual... information." We report the existence of similar multimodal neurons in artificial neural networks. This includes neurons selecting for prominent public figures or fictional characters, such as Lady Gaga or Spiderman. Like the biological multimodal neurons, these artificial neurons respond to the same subject in photographs, drawings, and images of their name. Authors: Gabriel Goh, Nick Cammarata, Chelsea Voss, Shan Carter, Michael Petrov, Ludwig Schubert, Alec Radford, Chris Olah
In this episode Dr. Usha Sridhar talks about her journey and the way mathematics has shaped it, her challenges as an educator, mother, student, immigrant and employee.Dr. Usha Sridhar is a Sripathi Gold medalist from Andhra University (topped in all Science departments' results and achieved University First). She complete two Ph.D in mathematics (yes 2 Ph.D) in the area of Analysis, Complex Variables and Proof Theory and Artificial Neural Networks. Apart from her great academic achievements, she has also worked in finance field for 8 years.Usha's passion about teaching, is nurtured by her parents. She has been teaching Mathematics, Numerical Techniques, Business, Statistics, Quantitative Methods and related subjects at various universities for more than three decades. Usha is part of the Teaching team won the prestigious UTS (University of Technology Sydney) Teaching citation award in 2011, 2018 and 2020.
David Yang, Ph.D., Co-founder Yva.ai, Founder and Board Director at ABBYY, member of Band of Angels, Silicon Valley based serial entrepreneur specializes in AI, founded 12 companies. David is a globally recognized thought leader, speaker and advisor in the areas of AI, Artificial Neural Networks, People Analytics, Smart 360, Peer-to-peer Continuous Listening, Organisation Network Analytics (ONA), HR metrics, talent measurement, workforce analytics, performance management and Organizational Change. He's the Founder & Chairman of the Board of ABBYY - world leading developer of AI, Content Intelligence, Text Analytics with 1300+ employees in 14 offices in 11 countries. More than 50 million users and thousands of enterprise customers in 200 countries rely on ABBYY's solutions including: PwC, McDonalds, Xerox, Toyota, Yum!Restaurants, Deloitte, PepsiCo, Volkswagen, UCSF. World leading RPA vendors, including UiPath, BluePrism, Robiquity among others rely on ABBYY's AI technologies. Currently David is dedicated to Yva.ai, the company that develops an Ethical People Analytics, Continuous Engagement and Performance Management Platform which helps organizations save millions of dollars by detecting burnout and predicting resignations of key employees. Yva makes 360 scalable, accurate and real-time. Each employee receives personal dashboards and recommendations. The Smart ONA helps executives find informal leaders to lead cross-functional collaboration, agile transformation and customer-focused experience. David created Cybiko, world first hand-held wireless communication computer for teenagers; co-founded iiko, new generation AI powered restaurant and hospitality industry solution; co-founded Plazius, a customer loyalty and mobile payment platform; founded a number of creative art-based ventures, including: FAQ-Café studio, DeFAQto; co-founded Ayb Educational Foundation and Ayb School. David is also a frequent keynote speaker at conferences and corporate events and author of numerous patents and scientific publications. FIND DAVID ON SOCIAL MEDIA LinkedIn | Facebook | Twitter | Instagram © Copyright 2022 Den of Rich. All rights reserved.
David Yang, Ph.D., Co-founder Yva.ai, Founder and Board Director at ABBYY, member of Band of Angels, Silicon Valley based serial entrepreneur specializes in AI, founded 12 companies.David is a globally recognized thought leader, speaker and advisor in the areas of AI, Artificial Neural Networks, People Analytics, Smart 360, Peer-to-peer Continuous Listening, Organisation Network Analytics (ONA), HR metrics, talent measurement, workforce analytics, performance management and Organizational Change.He's the Founder & Chairman of the Board of ABBYY - world leading developer of AI, Content Intelligence, Text Analytics with 1300+ employees in 14 offices in 11 countries. More than 50 million users and thousands of enterprise customers in 200 countries rely on ABBYY's solutions including: PwC, McDonalds, Xerox, Toyota, Yum!Restaurants, Deloitte, PepsiCo, Volkswagen, UCSF. World leading RPA vendors, including UiPath, BluePrism, Robiquity among others rely on ABBYY's AI technologies.Currently David is dedicated to Yva.ai, the company that develops an Ethical People Analytics, Continuous Engagement and Performance Management Platform which helps organizations save millions of dollars by detecting burnout and predicting resignations of key employees. Yva makes 360 scalable, accurate and real-time. Each employee receives personal dashboards and recommendations. The Smart ONA helps executives find informal leaders to lead cross-functional collaboration, agile transformation and customer-focused experience.David created Cybiko, world first hand-held wireless communication computer for teenagers; co-founded iiko, new generation AI powered restaurant and hospitality industry solution; co-founded Plazius, a customer loyalty and mobile payment platform; founded a number of creative art-based ventures, including: FAQ-Café studio, DeFAQto; co-founded Ayb Educational Foundation and Ayb School.David is also a frequent keynote speaker at conferences and corporate events and author of numerous patents and scientific publications.FIND DAVID ON SOCIAL MEDIALinkedIn | Facebook | Twitter | Instagram
One of the recent applications of neural networks has been in the field of art and music Gahan creativity be accomplished through artificial neural network artificial noodle networks are capable of some level of creativity although not on par with the human faculty what are the challenges of achieving music and art through algorithms what are the various approaches these are some of the questions we shall talk about in this episode --- Support this podcast: https://anchor.fm/nirmit-verma/support
Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2020.10.29.361410v1?rss=1 Authors: Lodder, R., Tiitto, M. V. Abstract: Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by inattention, hyperactivity, and impulsivity. Our lab is currently conducting a pilot study to assess the effects of the online game Minecraft as a therapeutic video game (TVG) to train executive function deficits in children with ADHD. The effect of the TVG intervention in combination with stimulants is being investigated to develop a drug-device combination therapy that can address both the dopaminergic dysfunction and executive function deficits present in ADHD. Although the results of this study will be used to guide the clinical development process, additional guidance for the optimization of the executive function training activities will be provided by a computational model of executive functions built with artificial neural networks (ANNs). This model uses ANNs to complete virtual tasks resembling the executive function training activities that the study subjects practice in the Minecraft world, and the schedule of virtual tasks that result in maximum improvements in ANN performance on these tasks will be investigated as a method to inform the selection of training regimens in future clinical studies. This study first proposes the use of recurrent neural networks to model the fluid intelligence executive function. This model is then combined with a previously developed model using convolutional neural networks to model working memory and prepotent impulsivity to produce virtual "subjects" who complete a computational simulation of a Time Management task that requires the use of both of these executive functions to complete. The capability of this model to produce groups of virtual subjects with significantly different levels of performance on the Time Management task is demonstrated. Copy rights belong to original authors. Visit the link for more info
Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2020.10.26.355990v1?rss=1 Authors: Lodder, R., Tiitto, M. V. Abstract: Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by inattention, hyperactivity, and impulsivity. The treatment of ADHD could potentially be improved with the development of combination therapies targeting multiple systems. Both the number of children diagnosed with ADHD and the use of stimulant medications for its treatment have been rising in recent years, and concern about side-effects and future problems that medication may cause have been increasing. An alternative treatment strategy for ADHD attracting wide interest is the targeting of neuropsychological functioning, such as executive function impairments. Computerized training programs (including video games) have drawn interest as a tool to train improvements in executive function deficits in children with ADHD. Our lab is currently conducting a pilot study to assess the effects of the online game Minecraft as a therapeutic video game (TVG) to train executive function deficits in children with ADHD. The effect of the TVG intervention in combination with stimulants is being investigated to develop a drug-device combination therapy that can address both the dopaminergic dysfunction and executive function deficits present in ADHD. Although the results of this study will be used to guide the clinical development process, additional guidance for the optimization of the executive function training activities will be provided by a computational model of executive functions built with artificial neural networks (ANNs). This model uses ANNs to complete virtual tasks resembling the executive function training activities that the study subjects practice in the Minecraft world, and the schedule of virtual tasks that result in maximum improvements in ANN performance on these tasks will be investigated as a method to inform the selection of training regimens in future clinical studies. Copy rights belong to original authors. Visit the link for more info
In this episode of DS30, our hosts, data science instructors Michael Cullen and Ana Hocevar are joined by Zach King, senior data scientist with Go Daddy, to discuss his work with Go Daddy and the differences between artificial neural networks and gradient boosted trees.Make sure to subscribe and tune in every other week for a new episode as Michael and Ana take on new topics pertaining to the field of data science.
In this episode #41, the hosts Naveen Samala & Sudhakar Nagandla have interacted with another guest Rohit. Rohit Gupta is a Technical Trainer, who holds a Master's degree in Informatics, from the University of Delhi, and a Bachelor's degree in Electronic Science, from the University of Delhi. He is also C# Corner MVP (Most Valuable professional), Author, Speaker. Rohit is deeply interested in the field of Artificial Intelligence, Machine Learning, and Python. His aim Is to make World's First Human-Like Humanoid. Rohit believes in the statement “bonding between Machines and Humans will make this world a better place. Listen to Rohit's Insights on: Basics of Neural Networks and its relation to AI, DS & ML. How Artificial Neural Networks (ANN) work? Types of Artificial Neural Networks Shallow Neural Networks or SNN and Deep Neural Networks or DNN Concept of Bias in ANN ANN project ideas for enthusiasts How ANN is different from Machine Learning? How to start learning ANN? Resources & Books for ANN Here are the resources shared by Rohit: NPTEL YouTube Channel: https://www.youtube.com/user/nptelhrd Website: https://nptel.ac.in/ Neural Network: https://bit.ly/3lLT8EX Krish Naik Complete Deep Learning: https://bit.ly/30RJ6K4 YouTube Channel: https://www.youtube.com/user/krishnaik06 Deep Learning with Keras: https://bit.ly/3lu0soc 3Blue1Brown YouTube Channel: https://bit.ly/2GDKVDT Neural Network Playlist: https://bit.ly/3dfqQiZ Sentdex YouTube Channel: https://www.youtube.com/user/sentdex Deep Learning Basics: https://bit.ly/30UWRrt Website: https://nnfs.io/ Deep Learning: C# Corner: https://www.c-sharpcorner.com/article/deep-learning/ Kaggle: https://www.kaggle.com/learn/deep-learning Coursera Nanodegree: https://www.udacity.com/course/deep-learning-nanodegree--nd101 TEDx: https://www.ted.com/search?q=deep+learning Andrew NG Course: https://www.coursera.org/learn/machine-learning Python Implementation of Andrew NG Course: https://bit.ly/3gNOofl Deeplearning.ai : https://www.deeplearning.ai/ Optimizing a Neural Network: https://www.c-sharpcorner.com/article/how-to-optimize-a-neural-network/ Machine Learning India LinkedIn: https://www.linkedin.com/company/mlindia/ Website: https://linktr.ee/mlindia Twitter: https://twitter.com/ml_india_ Instagram: https://instagram.com/ml.india Telegram: https://t.me/machinelearning24x7 Rohit Gupta LinkedIn: https://www.linkedin.com/in/rohit-gupta-ai/ Twitter: https://twitter.com/RohitGuptaAI Instagram: https://www.instagram.com/rohitgupta161093/ Facebook: https://www.facebook.com/rohit.gupta.33633 Gmail: gupta.rohitg.rohit900@gmail.com Telegram: https://t.me/rohit_gupta_ai C# Corner Profile: https://www.c-sharpcorner.com/members/rohit-gupta95 Enjoy the episode! Do not forget to share your suggestions or feedback at theguidingvoice4u@gmail.com or by messaging at +91 9494 587 187 Subscribe to our YouTube Channel: https://www.youtube.com/c/TheGuidingVoice Also, follow The Guiding Voice on Social Media: LinkedIn: https://www.linkedin.com/company/theguidingvoice Facebook: http://facebook.com/theguidingvoice4u Twitter: http://twitter.com/guidingvoice Instagram: https://www.instagram.com/theguidingvoice4u/ Pinterest: https://in.pinterest.com/theguidingvoice4u/pins/ #neuralnetworks, #NN, #artificialneuralnetworks, #ANN, #SNN, #DNN, #RNN #artificialIntelligence, #AI, #ML, #DataScience, #AIBasics, #KDNuggets, #MLIndia, #machinelearning, #bigdata, #datascience, #deeplearning, #supervisedlearning, #unsupervisedlearning, #Kaggle, #career, #jobs, #corona, #pandemic, #postpandemic, #careerguidance, #mentorship, #careerpath, #progression, #management, #leadership, #crisis, #job, #midcareer, #youngprofessionals, #careergraph, #TGV, #theguidingvoice
Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2020.09.27.315747v1?rss=1 Authors: Anand, A., Sen, S., Roy, K. Abstract: Quantifying the similarity between artificial neural networks (ANNs) and their biological counterparts is an important step towards building more brain-like artificial intelligence systems. Recent efforts in this direction use neural predictivity, or the ability to predict the responses of a biological brain given the information in an ANN (such as its internal activations), when both are presented with the same stimulus. We propose a new approach to quantifying neural predictivity by explicitly mapping the activations of an ANN to brain responses with a nonlinear function, and measuring the error between the predicted and actual brain responses. Further, we propose to use a neural network to approximate this mapping function by training it on a set of neural recordings. The proposed method was implemented within the Tensorflow framework and evaluated on a suite of 8 state-of-the-art image recognition ANNs. Our experiments suggest that the use of a non-linear mapping function leads to higher neural predictivity. Our findings also reaffirm the observation that the latest advances in classification performance of image recognition ANNs are not matched by improvements in their neural predictivity. Finally, we examine the impact of pruning, a widely used ANN optimization, on neural predictivity, and demonstrate that network sparsity leads to higher neural predictivity. Copy rights belong to original authors. Visit the link for more info
Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2020.08.13.250142v1?rss=1 Authors: Abdelmoula, W. M., Lopez, B. G.-C., Randall, E. C., Kapur, T., Sarkaria, J. N., White, F. M., Agar, J. N., Wells, W. M., Agar, N. Y. R. Abstract: Mass spectrometry imaging (MSI) is an emerging technology that holds potential for improving clinical diagnosis, biomarker discovery, metabolomics research and pharmaceutical applications. The large data size and high dimensional nature of MSI pose computational and memory complexities that hinder accurate identification of biologically-relevant molecular patterns. We propose msiPL, a robust and generic probabilistic generative model based on a fully-connected variational autoencoder for unsupervised analysis and peak learning of MSI data. The method can efficiently learn and visualize the underlying non-linear spectral manifold, reveal biologically-relevant clusters of tumor heterogeneity and identify underlying informative m/z peaks. The method provides a probabilistic parametric mapping to allow a trained model to rapidly analyze a new unseen MSI dataset in a few seconds. The computational model features a memory-efficient implementation using a minibatch processing strategy to enable the analyses of big MSI data (encompassing more than 1 million high-dimensional datapoints) with significantly less memory. We demonstrate the robustness and generic applicability of the application on MSI data of large size from different biological systems and acquired using different mass spectrometers at different centers, namely: 2D Matrix-Assisted Laser Desorption Ionization (MALDI) Fourier Transform Ion Cyclotron Resonance (FT ICR) MSI data of human prostate cancer, 3D MALDI Time-of-Flight (TOF) MSI data of human oral squamous cell carcinoma, 3D Desorption Electrospray Ionization (DESI) Orbitrap MSI data of human colorectal adenocarcinoma, 3D MALDI TOF MSI data of mouse kidney, and 3D MALDI FT ICR MSI data of a patient-derived xenograft (PDX) mouse brain model of glioblastoma. Copy rights belong to original authors. Visit the link for more info
Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2020.07.09.185116v1?rss=1 Authors: Hyodong Lee, Eshed Margalit, Kamila M. Jozwik, Michael A. Cohen, Nancy Kanwisher, Daniel L. K. Yamins, James J. DiCarlo Abstract: A salient characteristic of monkey inferior temporal (IT) cortex is the IT face processing network. Its hallmarks include: “face neurons” that respond more to faces than non-face objects, strong spatial clustering of those neurons in foci at each IT anatomical level (“face patches”), and the preferential interconnection of those foci. While some deep artificial neural networks (ANNs) are good predictors of IT neuronal responses, including face neurons, they do not explain those face network hallmarks. Here we ask if they might be explained with a simple, metabolically motivated addition to current ANN ventral stream models. Specifically, we designed and successfully trained topographic deep ANNs (TDANNs) to solve real-world visual recognition tasks (as in prior work), but, in addition, we also optimized each network to minimize a proxy for neuronal wiring length within its IT layers. We report that after this dual optimization, the model IT layers of TDANNs reproduce the hallmarks of the IT face network: the presence of face neurons, clusters of face neurons that quantitatively match those found in IT face patches, connectivity between those patches, and the emergence of face viewpoint invariance along the network hierarchy. We find that these phenomena emerge for a range of naturalistic experience, but not for highly unnatural training. Taken together, these results show that the IT face processing network could be a consequence of a basic hierarchical anatomy along the ventral stream, selection pressure on the visual system to accomplish general object categorization, and selection pressure to minimize axonal wiring length.Competing Interest StatementThe authors have declared no competing interest.View Full Text Copy rights belong to original authors. Visit the link for more info
Is artificial intelligence really going to change the way we live and work, or are the supposed possibilities no more than seductive PR? In this episode, alongside chief technologist Matt Armstrong-Barnes, we trace AI's technological leaps from Alan Turing to AlexNet via Dartmouth University. We map out the innovations impacting organisations right now by untangling strong and narrow AI, machine learning, deep learning, and artificial neural networks. From cybersecurity to big data, we ponder the good, the bad, and the uncanny side of AI; how to tread the ethical tightrope; and identify implementation tactics applicable to organisations of any size.
Link to bioRxiv paper: http://biorxiv.org/cgi/content/short/2020.06.26.174482v1?rss=1 Authors: Schrimpf, M., Blank, I. A., Tuckute, G., Kauf, C., Hosseini, E. A., KANWISHER, N. G., Tenenbaum, J. B., Fedorenko, E. Abstract: The ability to share ideas through language is our species' signature cognitive skill, but how this feat is achieved by the brain remains unknown. Inspired by the success of artificial neural networks (ANNs) in explaining neural responses in perceptual tasks (Kell et al., 2018; Khaligh-Razavi & Kriegeskorte, 2014; Schrimpf et al., 2018; Yamins et al., 2014; Zhuang et al., 2017), we here investigated whether state-of-the-art ANN language models (e.g. Devlin et al., 2018; Pennington et al., 2014; Radford et al., 2019) capture human brain activity elicited during language comprehension. We tested 43 language models spanning major current model classes on three neural datasets (including neuroimaging and intracranial recordings) and found that the most powerful generative transformer models (Radford et al., 2019) accurately predict neural responses, in some cases achieving near-perfect predictivity relative to the noise ceiling. In contrast, simpler word-based embedding models (e.g. Pennington et al., 2014) only poorly predict neural responses (
Uri Hasson joins us this week to discuss the paper Robust-fit to Nature: An Evolutionary Perspective on Biological (and Artificial) Neural Networks.
Neural networks is one of the most powerful and widely used algorithms when it comes to the sub field of machine learning called deep learning. The neural networks that we are going to considered are strictly called artificial neural networks, and as the name suggests, are based on what science knows about the human brain’s structure and function. Briefly, a neural network is defined as a computing system that consist of a number of simple but highly interconnected elements or nodes called Neurons , which are organized in layers which process information using dynamic state responses to external inputs. This algorithm is extremely useful, as we will explain later, in finding patterns that are too complex for being manually extracted and taught to recognize to the machine.We from BEPEC are ready to help you and make you shift your career at any cost.For more details visit: https://www.bepec.in/Bepec registration form : https://www.bepec.in/registration-formCheck our youtube channel for more videos and please subscribe: https://www.youtube.com/channel/UCn1U...Check our Instagram page: https://instagram.com/bepec_solutions/Check our Facebook Page : https://www.facebook.com/Bepecsolutions/For any help or for any guidance please email enquiry@bepec.in
This Episode explains how Artificial Neural Networks work in machine learning. How a neural network trains, what is a forward propagation, backward propagation, and transfer learning.
نتحدّث في هذه الحلقة مع كريستوف زغبي وريم محمود عن الذكاء الاصطناعي وفروعه المختلفة بالاضافة الى تطبيقاته الايجابية ونتطرّق أيضاً لبعض المخاطر والتحديات المستقبليةروابط:Beirut AI ---------LinkedIn: https://www.linkedin.com/company/beirutaiInstagram: https://www.instagram.com/beirut.ai/Facebook: https://www.facebook.com/BeirutAI/Twitter: https://twitter.com/beirutaiZaka-----Facebook: https://www.facebook.com/thisiszaka/Instagram: https://www.instagram.com/zaka.ai/LinkedIn: https://www.linkedin.com/company/zaka-ai/Twitter: https://twitter.com/zaka4ai Coder Voice-------------website: http://www.codervoice.comYouTube: https://www.youtube.com/channel/UCRyqGouRcBmnkFXjOyzdbBQFacebook: https://www.facebook.com/codervoiceInstagram: https://www.instagram.com/codervoiceTwitter: https://twitter.com/codervoice
In this episode I talk about my personal journey, how I became a Data Scientist. I start by talking about how I decided to go to college, what major to choose, how I chose my master’s degree. I talk about my time studying a PhD in Engineering and the most useful classes I took related to machine learning and data science. Finally, I briefly talk about my job experience as Data Scientist.
In this, our first episode, we will define the objective of the show as well as expectations. The show is designed for anyone who is interested in this fascinating world of Machine Learning.
En este episodio platicamos acerca de cómo convertirse en un Data Scientist (Científico de Datos). Empezamos hablando del perfil y expectativas de un Data Scientist (DS), ventajas de ser un DS, hablamos de los pre-requisitos antes de tomar cursos en data science, y por último damos recomendaciones de cursos gratuitos en línea para empezar a aprender.
Welcome to another episode of Develomentor. Today's guest is Dr. Chris Bouton. Dr Bouton is the CEO of Vyasa Analytics, applying novel deep learning (ie A.I.) approaches for life sciences and healthcare clients."Deep learning algorithms are basically the reason that everyone is talking about AI right now."--Dr. BoutonAs a kid, Chris Bouton loved sharks. Sharks turned into biology and biology turned into molecular biology, which evolved into computational biology. Chris followed his curiosity and received his Ph.D. in Neuroscience from Johns Hopkins University. In this episode we’ll also cover:Why did Chris bootstrap instead of raising money when starting EntagenWhy AI is just a fancy word for deep learningImportant personality traits for any entrepreneurHow Chris's Ph.D. in molecular neurobiology makes it extra satisfying to build AI algorithmsYou can find more resources and a full transcript in the show notesTo learn more about our podcast go to https://develomentor.com/To listen to previous episodes go to https://develomentor.com/blog/Follow Chris BoutonTwitter: @chrisboutonLinkedIn: linkedin.com/in/cbouton/Follow Develomentor:Twitter: @develomentorFollow Grant IngersollTwitter: @gsingersLinkedIn: linkedin.com/in/grantingersoll
Artificial intelligence has been in the news for a long time. Robert J. Marks airs one of his older interviews with Jim French on KIRO Radio to show the similarity to today’s reporting on artificial intelligence. Mind Matters News appreciates the permission of Jim French and KIRO Radio in Seattle to rebroadcast this interview. Show Notes 01:08 | Do computers Read More › Source
Artificial intelligence has been in the news for a long time. Robert J. Marks airs one of his older interviews with Jim French on KIRO Radio to show the similarity to today’s reporting on artificial intelligence. Mind Matters News appreciates the permission of Jim French and KIRO Radio in Seattle to rebroadcast this interview. Show Notes 01:08 | Do computers… Source
En este episodio seguimos revisamos los sets de datos más famosos en el mundo de Machine Learning esta vez haciendo uso de Kaggle donde aprendemos acerca de las tendencias y competencias actuales que van desde la detección de Deepfakes hasta la aplicación de Machine Learning en la NFL.
En este episodio revisamos los sets de datos más famosos en el mundo de Machine Learning haciendo uso del repositorio de la Universidad de California en Irvine donde aprendemos acerca de aplicaciones reales de Machine Learning para clasificar tipos de flores, para clasificar tipos de vinos, para predecir la calidad de vinos dada información bioquímica del proceso de elaboración, también vamos a ver como Machine Learning puede identificar oportunidades de compra de carros y por ultimo veremos cómo estas técnica pueden ser utilizadas para identificar enfermedades cardiacas en pacientes.
En este episodio definimos los conceptos de entrenamiento supervisado y entrenamiento no supervisado. Dentro del entrenamiento supervisado explicamos dos subcategorías: el entrenamiento supervisado para clasificación y el entramiento supervisado para regresión. Por último, mencionamos algunos ejemplos de algoritmos de Machine Learning populares para cada una de las categorías y subcategorías.
Este primer episodio esta dividido en 3 partes: 1) hablamos del objectivo de esta serie de podcast y hacia quien esta dirigido, 2) una introduccion formal del anfitrion Gustavo Lujan donde habla de su educacion y como llego a ser Data Scientist, 3) por ultimo hablamos de algunas definiciones relacionadas con Machine Learning.
Tommy discusses Artificial Neural Networks.
Topic Discussed : Future Technologies - Impact on the Defence MarketSpeaker: Ryan Keith PintoKey Takeaways:Learn what each technology potential is through 2030 and better understand which technologies will be the primary industry drivers in the short termIdentify the hottest technologies that will change the direction and landscape of the defence sectorIdentify the stages of maturity the different technologies are at present and the timeframe of impactIdentify growth opportunities in the defence sectorFor further insights, please join us for future podcasts and become a member of Frost & Sullivan’s Leadership Council by emailing us at: digital@frost.com or click here to Contact Us.Related Keywords: Frost & Sullivan, Small Modular Reactors (SMR), Transparent Photovoltaic Glass, Batteries, Electric and Pulse detonation engines, Hypersonic Propulsion, Directed Energy Weapons (DEW), Millimetre Wave Communication (5G), MANET Mesh Networks, Satcom on the Move (SOTM), Free Space Optics (FSO), Cloud Computing, Quantum Computing, Big data analytics, Artificial Neural Networks, Manned Unmanned Teaming (MUM-T), Swarm Robotics, Mixed Reality, Exoskeletons, Neuroelectronics, Blockchain in Cybersecurity, Metamaterials, Nanomaterials and smart materials, Additive Manufacturing (3D printing), Gallium Nitride (GaN), Photonics, Micro-Electro Mechanical Sensors (MEMS), Bionic Implants, Synthetic BiologyWebsite: www.frost.com See acast.com/privacy for privacy and opt-out information.
In Today’s Episode: We have a quick introduction into “Artificial Neural Networks”, What’s is it? Who developed it? And today’s Use of Neural Nets. We use them everyday In our phones, computers and home appliances. Etc. But what do they do? In this Episode, We will give a quick rundown of the Artificial Neural Net backstory brought to you By: Scientist and particle physicist: Singh and Dr. Anthony Barker.
AI / Machine Learning pioneer Andre Magni visits the pod to talk computer intelligence; from Microsoft's AI mission (to amplify human ingenuity with intelligent technology) to data-curation gotchas and modelling pitfalls to identifying dead bodies using AI. We even talks about our "AI Moms" and Andre's world-champion lure-coursing Pharaoh hounds. ----more---- Andre has been around Machine Learning and AI since 1994, on the early days of Artificial Neural Networks. He has developed and deployed an array of ML/AI solutions over the years, that range from cranio-facial identification to more normal ones as, speech and pattern recognition, anomaly detection, failure prediction and forecasts. Today, Andre leads a highly skilled team of Cloud Solutions Architect at Microsoft enabling customers to be successful on Azure. Lure-Coursing: https://www.akc.org/sports/coursing/lure-coursing/ Azure: https://azure.microsoft.com/en-us/ Get your Azure free account and start on AI today: https://azure.microsoft.com/en-us/free/ AI: https://www.microsoft.com/en-us/ai Bots: https://azure.microsoft.com/en-us/services/bot-service/ Machine Learning: https://azure.microsoft.com/en-us/overview/ai-platform/ The episode also features a pair of PSAs from two of our favorite kid-focused technology organizations MakeCode and Kodable. Give 'em some love (they do a great job!) PLEASE VISIT http://azureability.com for show notes and additional episodes. Also, if you like (or even hate!) what we're doing, please take the time to share your comments and suggestions either by the Podbean App (see links, below), email (lberman@microsoft.com) or Twitter (@azureability). CREDITS: Louis Berman (Host); Andre Magni (Guest); Gretchen Huebner (Kodable PSA), Simon Hillvo (MakeCode PSA); Vincent Tone / PremiumBeat (Music); Heather Walsh (Intro/Outro); Louis Berman (Engineer); East Coast Studio (Editing) TRANSCRIPT: https://www.videoindexer.ai/accounts/1c5a0342-11e8-4e1d-b656-d0bf35b80614/videos/f26d8e3451. PODCAST CLIENTS: You can find AzureABILITY on Apple Podcasts, Google Play and Spotify, or simply use our RSS Feed (http://www.azureability.com/feed.xml) and plug it into your podcast client of choice.
3.05 heralds baseball’s official return (0:39), announces the release date for the 2nd Book of Dust (5:04), expounds on the week’s algorithm club topic: Artificial Neural Networks (3:28), bounces around some players who are “unpredictable” that can be used during validation of predictive models (12:34), and reviews Tommy Pham (22:58).
Harry's guest in this episode is Massimo Buscema, director of the Semieon Research Center in Rome, Italy, and a full professor at the University of Colorado at Denver. Buscema researches and consults internationally on the theory and applications of AI, artificial neural networks, and evolutionary algorithms. The conversation focuses on AI and its applications in healthcare, and how it can enhance what we can see and uncover what we cannot. You can read a full transcript of this episode and browse all of our other episodes at glorikian.com/podcast/. How to rate MoneyBall Medicine on iTunes with an iPhone, iPad, or iPod touch: Launch the "Podcasts" app on your device. If you can't find this app, swipe all the way to the left on your home screen until you're on the Search page. Tap the search field at th top and type in "Podcasts." Apple's Podcasts app should show up in the search results. Tap the Podcasts app icon, and after it opens, tap the Search field at the top, or the little magnifying glass icon in the lower right corner. Type MoneyBall Medicine into the search field and press the Search button. In the search results, click on the MoneyBall Medicine logo. On the next page, scroll down until you see the Ratings & Reviews section. Below that you'll see five purple stars. Tap the stars to rate the show. Scroll down a little farther. You'll see a purple link saying "Write a Review." On the next screen, you'll see the stars again. You can tap them to leave a rating, if you haven't already. In the Title field, type a summary for your review. In the Review field, type your review. When you're finished, click Send. That's it, you're done. Thanks!
2.27 strategizes fantasy baseball through MLB standings watching (0:40), introduces the week’s algorithm challenge topic: Artificial Neural Networks (neural nets) (5:04), dives into some half baked neural net applications (14:53), punts a Fantasy Football conversation (22:56), and reviews Casino Royale (25:34).
Early in August, NYU professor Siddharth Garg checked for traffic, and put a yellow Post-it onto a stop sign outside the Brooklyn building in which he works. When he and two colleagues showed a photo of the scene to their road-sign detector software, it was 95 percent sure the stop sign in fact displayed a speed limit. The stunt demonstrated a potential security headache for engineers working with machine learning software.
Antonio and Jordy talk about artificial neural networks; these are algorithms that today seem synonymous with Artificial Intelligence. These algorithms, first introduced in the late 1950s, which mimic how the brain works are now being used extensively. We casually explore the history of ANNs, how these algorithms work, and what they can do. We expect Read More ...
Playwright James Graham talks to Anne McElvoy about his new comedy which puts Screaming Lord Sutch on stage. Graham's previous plays include The Vote, The Angry Brigade, This House. Historian Margaret MacMillan explores the question 'what difference do individuals make to history?' in her book History's People: Personalities and the Past. Figures include Bismarck, Babur and Roosevelt. Steve Furber, Professor of Computer Engineering at the University of Manchester, talks about his work on neural networks - constructing machines which work like parts of the human brain. He is joined by Tom Standage, digital editor at The Economist. New Generation Thinker Sam Goodman previews the BBC spy drama series The Night Manager, adapted from John Le Carre's 1993 novel. Monster Raving Loony is on at the Drum, Plymouth, from February 10th to 27th. Producer: Torquil Macleod.
Cognitive philosophers Richard Brown and Pete Mandik examine recent claims by Google researchers to have implemented dreams, imagery, and hallucinations in artificial neural networks. The images created by these artificial systems are kind of cool, but can anything at all be learned from such projects about how the mind or brain actually functions? Richard and Pete move from there to debate connectionism, AI, and rationalist vs. empiricist methodologies in the philosophy of cognitive science. Special prize for the first listener to correctly identify all three of the neuroscientists that Pete misidentifies!
In this episode, Audrow Nash interviews Kurosh Madani from the University of Paris-EST Créteil (UPEC) about neural networks. The talk begins with an overview of neural networks before discussing their possible applications.
In this episode, Audrow Nash interviews Kurosh Madani about neural networks and their applications.