Free artificial intelligence and machine learning video tutorial resource: November 2021

Tuesday, November 30, 2021

Kelompok 6 | Resume Video BISA AI "Tutorial Kalkulus Machine Learning"

Anggota Kelompok 6: 1. Vidya Adelia Anya 2. Debi Manda 3. Athalla Aqsha Suryoatmodjo

Monday, November 29, 2021

ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning (Paper Explained)

#ext5 #transferlearning #exmix The T5 model has been a staple for NLP research for the last years. Both its size and its approach to formulate all NLP tasks as prompt-based language modeling make it a convenient choice to tackle new challenges and provides a strong baseline for most current datasets. ExT5 pushes T5 to its limits by pre-training not only on self-supervised mask filling, but also at the same time on 107 different supervised NLP tasks, which is their new ExMix dataset. The resulting model compares very favorably to T5 when fine-tuned to downstream tasks. OUTLINE: 0:00 - Intro & Overview 2:15 - Recap: The T5 model 3:55 - The ExT5 model and task formulations 8:10 - ExMix dataset 9:35 - Do different tasks help each other? 16:50 - Which tasks should we include? 20:30 - Pre-Training vs Pre-Finetuning 23:00 - A few hypotheses about what's going on 27:20 - How much self-supervised data to use? 34:15 - More experimental results 38:40 - Conclusion & Summary Paper: https://ift.tt/3FYbs7B Abstract: Despite the recent success of multi-task learning and transfer learning for natural language processing (NLP), few works have systematically studied the effect of scaling up the number of tasks during pre-training. Towards this goal, this paper introduces ExMix (Extreme Mixture): a massive collection of 107 supervised NLP tasks across diverse domains and task-families. Using ExMix, we study the effect of multi-task pre-training at the largest scale to date, and analyze co-training transfer amongst common families of tasks. Through this analysis, we show that manually curating an ideal set of tasks for multi-task pre-training is not straightforward, and that multi-task scaling can vastly improve models on its own. Finally, we propose ExT5: a model pre-trained using a multi-task objective of self-supervised span denoising and supervised ExMix. Via extensive experiments, we show that ExT5 outperforms strong T5 baselines on SuperGLUE, GEM, Rainbow, Closed-Book QA tasks, and several tasks outside of ExMix. ExT5 also significantly improves sample efficiency while pre-training. Authors: Vamsi Aribandi, Yi Tay, Tal Schuster, Jinfeng Rao, Huaixiu Steven Zheng, Sanket Vaibhav Mehta, Honglei Zhuang, Vinh Q. Tran, Dara Bahri, Jianmo Ni, Jai Gupta, Kai Hui, Sebastian Ruder, Donald Metzler Links: TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ift.tt/3dJpBrR BitChute: https://ift.tt/38iX6OV LinkedIn: https://ift.tt/3qcgOFy BiliBili: https://ift.tt/3nlqFZS If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://ift.tt/2DuKOZ3 Patreon: https://ift.tt/390ewRH Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

Sunday, November 28, 2021

Gradient Descent Algorithm (GD Algorithm) | Deep Learning Tutorials | Society of AI

Deep Learning Tutorials In this video we discussed about GD Algorithm: Gradient Descent is the most common optimization algorithm in machine learning and deep learning. It is a first-order optimization algorithm. In above video we talk about GD Algorithm and Vectorized GD Algorithm: 1. Modified SN class. 2. Overall setup - What is the data, model, task. 3. Plotting functions - 3D, contour. 4. Individual algorithms and how they perform. 5. Exercise. Do write your views in the comment section. Subscribe for more videos. Follow us on: Website: https://www.societyofai.in/ LinkedIn: https://www.linkedin.com/company/soci... Facebook: https://www.facebook.com/societyofai/ Twitter: https://twitter.com/societyofai

Saturday, November 27, 2021

Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions (Paper Explained)

#imle #backpropagation #discrete Backpropagation is the workhorse of deep learning, but unfortunately, it only works for continuous functions that are amenable to the chain rule of differentiation. Since discrete algorithms have no continuous derivative, deep networks with such algorithms as part of them cannot be effectively trained using backpropagation. This paper presents a method to incorporate a large class of algorithms, formulated as discrete exponential family distributions, into deep networks and derives gradient estimates that can easily be used in end-to-end backpropagation. This enables things like combinatorial optimizers to be part of a network's forward propagation natively. OUTLINE: 0:00 - Intro & Overview 4:25 - Sponsor: Weights & Biases 6:15 - Problem Setup & Contributions 8:50 - Recap: Straight-Through Estimator 13:25 - Encoding the discrete problem as an inner product 19:45 - From algorithm to distribution 23:15 - Substituting the gradient 26:50 - Defining a target distribution 38:30 - Approximating marginals via perturb-and-MAP 45:10 - Entire algorithm recap 56:45 - Github Page & Example Paper: https://ift.tt/3HZ19lG Code (TF): https://ift.tt/3p9iQq7 Code (Torch): https://ift.tt/3w85ai5 Our Discord: https://ift.tt/3dJpBrR Sponsor: Weights & Biases https://wandb.com Abstract: Combining discrete probability distributions and combinatorial optimization problems with neural network components has numerous applications but poses several challenges. We propose Implicit Maximum Likelihood Estimation (I-MLE), a framework for end-to-end learning of models combining discrete exponential family distributions and differentiable neural components. I-MLE is widely applicable as it only requires the ability to compute the most probable states and does not rely on smooth relaxations. The framework encompasses several approaches such as perturbation-based implicit differentiation and recent methods to differentiate through black-box combinatorial solvers. We introduce a novel class of noise distributions for approximating marginals via perturb-and-MAP. Moreover, we show that I-MLE simplifies to maximum likelihood estimation when used in some recently studied learning settings that involve combinatorial solvers. Experiments on several datasets suggest that I-MLE is competitive with and often outperforms existing approaches which rely on problem-specific relaxations. Authors: Mathias Niepert, Pasquale Minervini, Luca Franceschi Links: TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ift.tt/3dJpBrR BitChute: https://ift.tt/38iX6OV LinkedIn: https://ift.tt/3qcgOFy BiliBili: https://ift.tt/3nlqFZS If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://ift.tt/2DuKOZ3 Patreon: https://ift.tt/390ewRH Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

Gradient Descent Algorithm (GD Algorithm) | Deep Learning Tutorials | Society of AI

Man VS Machine: Who Plays Table Tennis Better? 🤖

❤️ Check out Lambda here and sign up for their GPU Cloud: https://ift.tt/35NkCT7 📝 The paper "Optimal Stroke Learning with Policy Gradient Approach for Robotic Table Tennis" is available here: https://ift.tt/3G8KM4r https://www.youtube.com/watch?v=SNnqtGLmX4Y ❤️ Watch these videos in early access on our Patreon page or join us here on YouTube: - https://ift.tt/2icTBUb - https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg/join 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bryan Learn, Christian Ahlin, Eric Martel, Gordon Child, Ivo Galic, Jace O'Brien, Javier Bustamante, John Le, Jonas, Kenneth Davis, Klaus Busse, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Mark Oates, Michael Albrecht, Michael Tedder, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Rajarshi Nigam, Ramsey Elbasheer, Steef, Taras Bobrovytsky, Thomas Krcmar, Timothy Sum Hon Mun, Torsten Reil, Tybie Fitzhugh, Ueli Gallizzi. If you wish to appear here or pick up other perks, click here: https://ift.tt/2icTBUb Thumbnail background design: Felícia Zsolnai-Fehér - http://felicia.hu Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://ift.tt/2TnVBd3 Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/twominutepapers Web: https://ift.tt/1NwkG9m

Friday, November 26, 2021

Deep Learning for NLP - 17 (KAIST AI605 Fall 2021)

Course website: https://seominjoon.github.io/kaist-ai605/

Mitigating Overfitting and Underfitting with Dropout, Regularization - Full Stack Deep Learning

Overfitting and Underfitting are very common problems faced when training Deep Learning Models. In this tutorial, we shall see how to solve these problems via Data augmentation, Data collection, dropout, regularization, early stopping, less complex models, hyperparameter tuning, normalization. Previous (Introductory): https://youtu.be/GW3VadqOUnU Previous (Tensors and Variables): https://youtu.be/Kg2OgVHSH2o1 Previous (Linear Regression for Car Price Prediction): https://youtu.be/Y7DsfKyBF7g Previous (Convolutional Neural Networks for Malaria Diagnosis): https://youtu.be/MthqOrx_1Gk Previous (Loading and Saving TensorFlow Model to Gdrive): https://youtu.be/0U7IimAAC5Y Previous (Functional API, Model Subclassing and Custom Layers): https://youtu.be/wQz36Cmhe40 Previous (Performance Measurement): https://youtu.be/rqCzLNKJEvY Previous (Callbacks with TensorFlow 2): https://youtu.be/E_Ipd2LzTBw Colab Notebook: https://colab.research.google.com/drive/1uUH-asz3CFxlvld8uGx-m3crr4Iepp3u#scrollTo=ATnj3IWceW69 Check out our Deep Learning with TensorFlow 2 course (https://www.neuralearn.ai/course_page/3/). Check out our Deep Learning for Computer Vision with TensorFlow 2 course (https://www.neuralearn.ai/course_page/5/). Check out our Complete Linear Algebra Course https://www.neuralearn.ai/course_page/1/ Feel free to ask any questions. Always stay updated https://www.neuralearn.ai/subscribe/ Connect with us here: Twitter: https://twitter.com/neulearndotai Facebook: linkhttps://www.facebook.com/Neuralearnai-107372484374170/ LinkedIn https://www.linkedin.com/company/neuralearn

Thursday, November 25, 2021

Peer Review is still BROKEN! The NeurIPS 2021 Review Experiment (results are in)

#neurips #peerreview #machinelearning A look at the results of the 2021 NeurIPS peer review experiment. https://ift.tt/3EFUTgS https://ift.tt/3xa2dhz Links: TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ift.tt/3dJpBrR BitChute: https://ift.tt/38iX6OV LinkedIn: https://ift.tt/3qcgOFy BiliBili: https://ift.tt/3nlqFZS If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://ift.tt/2DuKOZ3 Patreon: https://ift.tt/390ewRH Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

Can We Simulate A Virtual Sponge? 🧽

❤️ Check out Weights & Biases and say hi in their community forum here: https://ift.tt/3DRsoMs 📝 The paper "Unified particle system for multiple-fluid flow and porous material" is available here: https://ift.tt/3HVlFDw https://ift.tt/3CPy0FB Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://ift.tt/2TnVBd3 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bryan Learn, Christian Ahlin, Eric Martel, Gordon Child, Ivo Galic, Jace O'Brien, Javier Bustamante, John Le, Jonas, Kenneth Davis, Klaus Busse, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Mark Oates, Michael Albrecht, Michael Tedder, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Rajarshi Nigam, Ramsey Elbasheer, Steef, Taras Bobrovytsky, Thomas Krcmar, Timothy Sum Hon Mun, Torsten Reil, Tybie Fitzhugh, Ueli Gallizzi. If you wish to appear here or pick up other perks, click here: https://ift.tt/2icTBUb Thumbnail background design: Felícia Zsolnai-Fehér - http://felicia.hu Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/twominutepapers Web: https://ift.tt/1NwkG9m

Wednesday, November 24, 2021

Parameter Prediction for Unseen Deep Architectures (w/ First Author Boris Knyazev)

#deeplearning #neuralarchitecturesearch #metalearning Deep Neural Networks are usually trained from a given parameter initialization using SGD until convergence at a local optimum. This paper goes a different route: Given a novel network architecture for a known dataset, can we predict the final network parameters without ever training them? The authors build a Graph-Hypernetwork and train on a novel dataset of various DNN-architectures to predict high-performing weights. The results show that not only can the GHN predict weights with non-trivial performance, but it can also generalize beyond the distribution of training architectures to predict weights for networks that are much larger, deeper, or wider than ever seen in training. OUTLINE: 0:00 - Intro & Overview 6:20 - DeepNets-1M Dataset 13:25 - How to train the Hypernetwork 17:30 - Recap on Graph Neural Networks 23:40 - Message Passing mirrors forward and backward propagation 25:20 - How to deal with different output shapes 28:45 - Differentiable Normalization 30:20 - Virtual Residual Edges 34:40 - Meta-Batching 37:00 - Experimental Results 42:00 - Fine-Tuning experiments 45:25 - Public reception of the paper ERRATA: - Boris' name is obviously Boris, not Bori - At 36:05, Boris mentions that they train the first variant, yet on closer examination, we decided it's more like the second Paper: https://ift.tt/3mhBKuz Code: https://ift.tt/3BjLTv6 Abstract: Deep learning has been successful in automating the design of features in machine learning pipelines. However, the algorithms optimizing neural network parameters remain largely hand-designed and computationally inefficient. We study if we can use deep learning to directly predict these parameters by exploiting the past knowledge of training other networks. We introduce a large-scale dataset of diverse computational graphs of neural architectures - DeepNets-1M - and use it to explore parameter prediction on CIFAR-10 and ImageNet. By leveraging advances in graph neural networks, we propose a hypernetwork that can predict performant parameters in a single forward pass taking a fraction of a second, even on a CPU. The proposed model achieves surprisingly good performance on unseen and diverse networks. For example, it is able to predict all 24 million parameters of a ResNet-50 achieving a 60% accuracy on CIFAR-10. On ImageNet, top-5 accuracy of some of our networks approaches 50%. Our task along with the model and results can potentially lead to a new, more computationally efficient paradigm of training networks. Our model also learns a strong representation of neural architectures enabling their analysis. Authors: Boris Knyazev, Michal Drozdzal, Graham W. Taylor, Adriana Romero-Soriano Links: TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ift.tt/3dJpBrR BitChute: https://ift.tt/38iX6OV LinkedIn: https://ift.tt/3qcgOFy BiliBili: https://ift.tt/3nlqFZS If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://ift.tt/2DuKOZ3 Patreon: https://ift.tt/390ewRH Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

Monday, November 22, 2021

Help Protect the Great Barrier Reef with Machine Learning

We are excited to announce a TensorFlow-sponsored Kaggle challenge to locate and identify harmful crown-of-thorns starfish (COTS), as part of a broader partnership between the Commonwealth Scientific and Industrial Research Organization (CSIRO) and Google, to help protect coral reefs everywhere. Join the challenge today at https://goo.gle/reef Subscribe to the TensorFlow channel → https://goo.gle/TensorFlow

Sunday, November 21, 2021

PDF(Probability Density Function) | Probability and Statistics for Machine Learning

PDF(Probability Density Function) | Probability and Statistics for Machine Learning t is a series of videos about Probability and statistics with code. machinelearningprojectforbeginners mlproject fastapi serving machine learning model using fasapi how to save machine learning model end to end machine learning project how to do binary classification how to do multiclass classification how to save machine learning model how to deploy machine learning model how to use count vectorizer how to code naive Bayes naive Bayes logistic regression Bert transformer data science case study data science project data science case study for beginners data science project beginners #tensorflow #ailearning #datasciencetutorial #machinelearningtutorial #neuralnetwork #datascince #datascincetutorial #machinelearning #machinelearningtutorial #deeplearning #multilayerperceptron #attentionlayer #transformer #bert #tensorflow #keras #deeplearninginhindi Neural Network Deep learning Machine learning mnistdigit recognition python mnist data set mnist TensorFlow tutorial mnist data set neural network mnist dataset python mnist digit recognation python cnn mnist dataset tensorflow mnist classification using cnn mnist project mnist digit recognation tensorflow mnist dataset for handwrittem digits mnist datasetcolab mnist dataset in colab mnist dataset neural network mnist dataset explained Handwritten digit recognation on MNIST data tensorflow tutorial tensorflow object detection tensorflow js tensorflow tutorial for beginners tensorflow tutorial in hindi tensorflow python tensorflow projects tensorflow installation tensorflow lite android tutorial tensorflow lite tensorflow object detection api tutorial tensorflow in hindi tensorflow js tutorial tensorflow certification keras tutorial keras tutorial for beginners keras vs tensorflow keras tuner tensorflow keras tutorial tensorflow keras image classification tensorflow keras install on windows tensorflow keras regression tensorflow keras object detection tutorial tensorflow keras example objectdetection tensorflow keras cnn tensorflow keras gpu tensorflow keras tutorials for beginners tensorflow keras example tensorflow keras install anaconda tensorflow keras rnn recurrent neural network in hindi recurrent neural network tutorial recurrent neural network python data science for beginners data science course data science full course data science interview question data science tutorial data science project data science in hindi data science interview data science python data science projects for beginners data science roadmap data science for beginners in hindi machine learning tutorial machine learning projects machine learning full course machine learning interview question machine learning in hindi machine learning roadmap machine learning projects in python machine learning tutorial in hindi deep learning tutorial deep learning ai deep learning python deep learning projects deep learning in hindi deep learning full course deep learning tutorial in hindi natural language processing in artifitial intelligence natural language processing python natural language processing tutorial natural language processing full course natural language processing projects natural language processing tutorial in hindi natural language processing course natural language processing in artifitial intelligence in hindi natural language processing in python NLP technique NLP training videos NLP techniques in hindi NLP in artifitial intelligence NLP projects in python NLP tutorial NLP course artificial intelligence tutorial artificial intelligence course artificial intelligence in hindi artificial intelligence robot and machine learning artificial intelligence tutorials in hindi artificial intelligence full course data scintist career data scintist course data scintist salary in india data scintist interview data scintist tutorial data science job salary in india data scintist job opportunites in india data scintist job role data scintist job opportunity data scintist job profile data scintist job interview data scintist job interview questions data scintist job for fresher data scintist job guarentee data scintist job description data analytic exel data analytic hindi data analytic lifecycle data analytic interview question data analytic project data analytic vs data science data analytic with python nptel assignment data analytic with python

Saturday, November 20, 2021

Code walkthrough Percentile,Percentilerank,CDF, Quantiles,IQR,median|Statistics For Machine Learning

percentile, percentile rank, CDF, quantiles,IQR, median Probability and Statistics For Machine Learning It is a series of videos about Probability and statistics with code. machinelearningprojectforbeginners mlproject fastapi serving machine learning model using fasapi how to save machine learning model end to end machine learning project how to do binary classification how to do multiclass classification how to save machine learning model how to deploy machine learning model how to use count vectorizer how to code naive Bayes naive Bayes logistic regression Bert transformer data science case study data science project data science case study for beginners data science project beginners #tensorflow #ailearning #datasciencetutorial #machinelearningtutorial #neuralnetwork #datascince #datascincetutorial #machinelearning #machinelearningtutorial #deeplearning #multilayerperceptron #attentionlayer #transformer #bert #tensorflow #keras #deeplearninginhindi Neural Network Deep learning Machine learning mnistdigit recognition python mnist data set mnist TensorFlow tutorial mnist data set neural network mnist dataset python mnist digit recognation python cnn mnist dataset tensorflow mnist classification using cnn mnist project mnist digit recognation tensorflow mnist dataset for handwrittem digits mnist datasetcolab mnist dataset in colab mnist dataset neural network mnist dataset explained Handwritten digit recognation on MNIST data tensorflow tutorial tensorflow object detection tensorflow js tensorflow tutorial for beginners tensorflow tutorial in hindi tensorflow python tensorflow projects tensorflow installation tensorflow lite android tutorial tensorflow lite tensorflow object detection api tutorial tensorflow in hindi tensorflow js tutorial tensorflow certification keras tutorial keras tutorial for beginners keras vs tensorflow keras tuner tensorflow keras tutorial tensorflow keras image classification tensorflow keras install on windows tensorflow keras regression tensorflow keras object detection tutorial tensorflow keras example objectdetection tensorflow keras cnn tensorflow keras gpu tensorflow keras tutorials for beginners tensorflow keras example tensorflow keras install anaconda tensorflow keras rnn recurrent neural network in hindi recurrent neural network tutorial recurrent neural network python data science for beginners data science course data science full course data science interview question data science tutorial data science project data science in hindi data science interview data science python data science projects for beginners data science roadmap data science for beginners in hindi machine learning tutorial machine learning projects machine learning full course machine learning interview question machine learning in hindi machine learning roadmap machine learning projects in python machine learning tutorial in hindi deep learning tutorial deep learning ai deep learning python deep learning projects deep learning in hindi deep learning full course deep learning tutorial in hindi natural language processing in artifitial intelligence natural language processing python natural language processing tutorial natural language processing full course natural language processing projects natural language processing tutorial in hindi natural language processing course natural language processing in artifitial intelligence in hindi natural language processing in python NLP technique NLP training videos NLP techniques in hindi NLP in artifitial intelligence NLP projects in python NLP tutorial NLP course artificial intelligence tutorial artificial intelligence course artificial intelligence in hindi artificial intelligence robot and machine learning artificial intelligence tutorials in hindi artificial intelligence full course data scintist career data scintist course data scintist salary in india data scintist interview data scintist tutorial data science job salary in india data scintist job opportunites in india data scintist job role data scintist job opportunity data scintist job profile data scintist job interview data scintist job interview questions data scintist job for fresher data scintist job guarentee data scintist job description data analytic exel data analytic hindi data analytic lifecycle data analytic interview question data analytic project data analytic vs data science data analytic with python nptel assignment data analytic with python

PDF(Probability Density Function) | Probability and Statistics for Machine Learning

Learning Rate Grafting: Transferability of Optimizer Tuning (Machine Learning Research Paper Reivew)

#grafting #adam #sgd The last years in deep learning research have given rise to a plethora of different optimization algorithms, such as SGD, AdaGrad, Adam, LARS, LAMB, etc. which all claim to have their special peculiarities and advantages. In general, all algorithms modify two major things: The (implicit) learning rate schedule, and a correction to the gradient direction. This paper introduces grafting, which allows to transfer the induced learning rate schedule of one optimizer to another one. In that, the paper shows that much of the benefits of adaptive methods (e.g. Adam) are actually due to this schedule, and not necessarily to the gradient direction correction. Grafting allows for more fundamental research into differences and commonalities between optimizers, and a derived version of it makes it possible to computes static learning rate corrections for SGD, which potentially allows for large savings of GPU memory. OUTLINE 0:00 - Rant about Reviewer #2 6:25 - Intro & Overview 12:25 - Adaptive Optimization Methods 20:15 - Grafting Algorithm 26:45 - Experimental Results 31:35 - Static Transfer of Learning Rate Ratios 35:25 - Conclusion & Discussion Paper (OpenReview): https://ift.tt/30IA84C Old Paper (Arxiv): https://ift.tt/3HFueT2 Our Discord: https://ift.tt/3dJpBrR Abstract: In the empirical science of training large neural networks, the learning rate schedule is a notoriously challenging-to-tune hyperparameter, which can depend on all other properties (architecture, optimizer, batch size, dataset, regularization, ...) of the problem. In this work, we probe the entanglements between the optimizer and the learning rate schedule. We propose the technique of optimizer grafting, which allows for the transfer of the overall implicit step size schedule from a tuned optimizer to a new optimizer, preserving empirical performance. This provides a robust plug-and-play baseline for optimizer comparisons, leading to reductions to the computational cost of optimizer hyperparameter search. Using grafting, we discover a non-adaptive learning rate correction to SGD which allows it to train a BERT model to state-of-the-art performance. Besides providing a resource-saving tool for practitioners, the invariances discovered via grafting shed light on the successes and failure modes of optimizers in deep learning. Authors: Anonymous (Under Review) Links: TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ift.tt/3dJpBrR BitChute: https://ift.tt/38iX6OV LinkedIn: https://ift.tt/3qcgOFy BiliBili: https://ift.tt/3nlqFZS If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://ift.tt/2DuKOZ3 Patreon: https://ift.tt/390ewRH Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

Sculpting Liquids in Virtual Reality! 🍷

❤️ Check out Weights & Biases and sign up for a free demo here: https://ift.tt/2S5tXnb 📝 The paper "Interactive Liquid Splash Modeling by User Sketches" is available here: https://ift.tt/3oMajZV https://ift.tt/3iOpn7u 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bryan Learn, Christian Ahlin, Eric Martel, Gordon Child, Ivo Galic, Jace O'Brien, Javier Bustamante, John Le, Jonas, Kenneth Davis, Klaus Busse, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Mark Oates, Michael Albrecht, Michael Tedder, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Rajarshi Nigam, Ramsey Elbasheer, Steef, Taras Bobrovytsky, Thomas Krcmar, Timothy Sum Hon Mun, Torsten Reil, Tybie Fitzhugh, Ueli Gallizzi. If you wish to appear here or pick up other perks, click here: https://ift.tt/2icTBUb Thumbnail background design: Felícia Zsolnai-Fehér - http://felicia.hu Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://ift.tt/2TnVBd3 Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/twominutepapers Web: https://ift.tt/1NwkG9m #vr

Friday, November 19, 2021

Intro to AI

Median,IQR(InterQuartile Range),Quantile | Probability and Statistics For Machine Learning

Probability and Statistics For Machine Learning It is a series of videos about Probability and statistics with code. machinelearningprojectforbeginners mlproject fastapi serving machine learning model using fasapi how to save machine learning model end to end machine learning project how to do binary classification how to do multiclass classification how to save machine learning model how to deploy machine learning model how to use count vectorizer how to code naive Bayes naive Bayes logistic regression Bert transformer data science case study data science project data science case study for beginners data science project beginners #tensorflow #ailearning #datasciencetutorial #machinelearningtutorial #neuralnetwork #datascince #datascincetutorial #machinelearning #machinelearningtutorial #deeplearning #multilayerperceptron #attentionlayer #transformer #bert #tensorflow #keras #deeplearninginhindi Neural Network Deep learning Machine learning mnistdigit recognition python mnist data set mnist TensorFlow tutorial mnist data set neural network mnist dataset python mnist digit recognation python cnn mnist dataset tensorflow mnist classification using cnn mnist project mnist digit recognation tensorflow mnist dataset for handwrittem digits mnist datasetcolab mnist dataset in colab mnist dataset neural network mnist dataset explained Handwritten digit recognation on MNIST data tensorflow tutorial tensorflow object detection tensorflow js tensorflow tutorial for beginners tensorflow tutorial in hindi tensorflow python tensorflow projects tensorflow installation tensorflow lite android tutorial tensorflow lite tensorflow object detection api tutorial tensorflow in hindi tensorflow js tutorial tensorflow certification keras tutorial keras tutorial for beginners keras vs tensorflow keras tuner tensorflow keras tutorial tensorflow keras image classification tensorflow keras install on windows tensorflow keras regression tensorflow keras object detection tutorial tensorflow keras example objectdetection tensorflow keras cnn tensorflow keras gpu tensorflow keras tutorials for beginners tensorflow keras example tensorflow keras install anaconda tensorflow keras rnn recurrent neural network in hindi recurrent neural network tutorial recurrent neural network python data science for beginners data science course data science full course data science interview question data science tutorial data science project data science in hindi data science interview data science python data science projects for beginners data science roadmap data science for beginners in hindi machine learning tutorial machine learning projects machine learning full course machine learning interview question machine learning in hindi machine learning roadmap machine learning projects in python machine learning tutorial in hindi deep learning tutorial deep learning ai deep learning python deep learning projects deep learning in hindi deep learning full course deep learning tutorial in hindi natural language processing in artifitial intelligence natural language processing python natural language processing tutorial natural language processing full course natural language processing projects natural language processing tutorial in hindi natural language processing course natural language processing in artifitial intelligence in hindi natural language processing in python NLP technique NLP training videos NLP techniques in hindi NLP in artifitial intelligence NLP projects in python NLP tutorial NLP course artificial intelligence tutorial artificial intelligence course artificial intelligence in hindi artificial intelligence robot and machine learning artificial intelligence tutorials in hindi artificial intelligence full course data scintist career data scintist course data scintist salary in india data scintist interview data scintist tutorial data science job salary in india data scintist job opportunites in india data scintist job role data scintist job opportunity data scintist job profile data scintist job interview data scintist job interview questions data scintist job for fresher data scintist job guarentee data scintist job description data analytic exel data analytic hindi data analytic lifecycle data analytic interview question data analytic project data analytic vs data science data analytic with python nptel assignment data analytic with python

Code walkthrough Percentile,Percentilerank,CDF, Quantiles,IQR,median|Statistics For Machine Learning

Thursday, November 18, 2021

Hello Ai Introduction to Machine Learning 2-1

This is the day two of the Hello Ai webinar with Edward pie

Outliers | Probability and Statistics For Machine Learning

Probability and Statistics For Machine Learning machinelearningprojectforbeginners mlproject fastapi serving machine learning model using fasapi how to save machine learning model end to end machine learning project how to do binary classification how to do multiclass classification how to save machine learning model how to deploy machine learning model how to use count vectorizer how to code naive Bayes naive Bayes logistic regression Bert transformer data science case study data science project data science case study for beginners data science project beginners #tensorflow #ailearning #datasciencetutorial #machinelearningtutorial #neuralnetwork #datascince #datascincetutorial #machinelearning #machinelearningtutorial #deeplearning #multilayerperceptron #attentionlayer #transformer #bert #tensorflow #keras #deeplearninginhindi Neural Network Deep learning Machine learning mnistdigit recognition python mnist data set mnist TensorFlow tutorial mnist data set neural network mnist dataset python mnist digit recognation python cnn mnist dataset tensorflow mnist classification using cnn mnist project mnist digit recognation tensorflow mnist dataset for handwrittem digits mnist datasetcolab mnist dataset in colab mnist dataset neural network mnist dataset explained Handwritten digit recognation on MNIST data tensorflow tutorial tensorflow object detection tensorflow js tensorflow tutorial for beginners tensorflow tutorial in hindi tensorflow python tensorflow projects tensorflow installation tensorflow lite android tutorial tensorflow lite tensorflow object detection api tutorial tensorflow in hindi tensorflow js tutorial tensorflow certification keras tutorial keras tutorial for beginners keras vs tensorflow keras tuner tensorflow keras tutorial tensorflow keras image classification tensorflow keras install on windows tensorflow keras regression tensorflow keras object detection tutorial tensorflow keras example objectdetection tensorflow keras cnn tensorflow keras gpu tensorflow keras tutorials for beginners tensorflow keras example tensorflow keras install anaconda tensorflow keras rnn recurrent neural network in hindi recurrent neural network tutorial recurrent neural network python data science for beginners data science course data science full course data science interview question data science tutorial data science project data science in hindi data science interview data science python data science projects for beginners data science roadmap data science for beginners in hindi machine learning tutorial machine learning projects machine learning full course machine learning interview question machine learning in hindi machine learning roadmap machine learning projects in python machine learning tutorial in hindi deep learning tutorial deep learning ai deep learning python deep learning projects deep learning in hindi deep learning full course deep learning tutorial in hindi natural language processing in artifitial intelligence natural language processing python natural language processing tutorial natural language processing full course natural language processing projects natural language processing tutorial in hindi natural language processing course natural language processing in artifitial intelligence in hindi natural language processing in python NLP technique NLP training videos NLP techniques in hindi NLP in artifitial intelligence NLP projects in python NLP tutorial NLP course artificial intelligence tutorial artificial intelligence course artificial intelligence in hindi artificial intelligence robot and machine learning artificial intelligence tutorials in hindi artificial intelligence full course data scintist career data scintist course data scintist salary in india data scintist interview data scintist tutorial data science job salary in india data scintist job opportunites in india data scintist job role data scintist job opportunity data scintist job profile data scintist job interview data scintist job interview questions data scintist job for fresher data scintist job guarentee data scintist job description data analytic exel data analytic hindi data analytic lifecycle data analytic interview question data analytic project data analytic vs data science data analytic with python nptel assignment data analytic with python

CDF(Cumulative Distribution Function) | Probability and Statistics For Machine Learning

BASIC INPUT/OUTPUT I/O IN TEXT FILE | VARIOUS MODE OF OPENING TEXT FILE IN PYTHON | VIDEO 13

Hey everyone This is Ujjwal kapil B.tech 2nd year Ai and Ml this we are starting are series in which we are covering every basic concept of Python programming Language I assure you that if you continue ths series with me you will be able to solve basic question of python and we are also going to do live question practice of python so what you have to do is just subscribe the channel so that you can get every video and update on time Join us on telegram Group https://t.me/Ujjwalkapil09 Website: https://sarkaricollege.ml All weekly episode are available on Spotify https://open.spotify.com/episode/7FlM... Jiosaavn https://www.jiosaavn.com/shows/the-sp... google podcast https://www.google.com/podcasts?feed=... anchor.fm https://anchor.fm/ujjwal-kapil/episod... follow me on Instagram https://www.instagram.com/ujjwal091102/ Facebook -https://www.facebook.com/ujjwal.kapil.90 Mic I use -----https://amzn.to/3jcV0Yb Laptop --- https://amzn.to/3vzmpZD phone used while recording-- https://amzn.to/2XmBeln engineering drawing,engineering graphics,engineering drawing 1st year,engineering,engineering drawing basics,subhodaya engineering drawing,introduction to engineering drawing,engineering drawing for 1st year,engineering graphics for first year engineering,engineering drawing in hindi,1st year engineering syallbus,iti engineering drawing,engineering drawing by subhodaya,b.tech 1st year syllabus,engineering drawings,engineering mathematics 1st year maths #python #pythonprogramming #pythontutorial #pythontutorialforbeginners #pythontutorialforbeginnersinhindi #ujjwalkapil #artificial intelligence,#machine learning,what is artificial intelligence,artificial intelligence tutorial,artificial intelligence and machine learning,machine learning vs artificial intelligence,artificial intelligence tutorial for beginners,machine learning tutorial,simplilearn artificial intelligence,artificial intelligence explained,artificial intelligence course,artificial intelligence edureka,artificial intelligence vs machine learning vs deep learning PANTNAGAR govind ballabh pant institute of engineering and technology pauri pauri garwal govind ballabh pant university of agriculture and technology

Anaconda, Python, Machine Learning & AI Code - 100 Day Challenge Day #3

I'm totally new to Anaconda, Python, ML and AI. I'm going through a 100 Days Of Python challenge to see what can be achieved. This is Day #3 of my journey of using Anaconda and Python for Windows and learning Python. Find a beginners Python tutorial and run my first Python code using VSCode and Anaconda. Fantastic work Gary! Thank you so much for the tutorial. Making my #100DaysOfPython Day3 so easy! Gary Explains Channel https://www.youtube.com/channel/UCRjSO-juFtngAeJGJRMdIZw Gary Explains Python Tutorial - Your First Program - https://www.youtube.com/watch?v=bF3ZZcNbtMg #Python #AnacondaCON #100DaysOfPython #Data #DataAnalytics #AI #MachineLearning #BigData

[ML News] Cedille French Language Model | YOU Search Engine | AI Finds Profitable MEME TOKENS

#mlnews #cedille #wmt Only the greatest of news from the world of Machine Learning. OUTLINE: 0:00 - Sponsor: Weights & Biases 1:50 - Cedille - French Language Model 3:55 - Facebook AI Multilingual model wins WMT 5:50 - YOU private search engine 10:35 - DeepMind's Open-Source Arnheim 12:10 - Company sued for using AI to make website more accessible 18:05 - Alibaba DAMO Academy creates 10 Trillion M6 model 21:15 - AMD MI200 Family 22:30 - State of AI report 2021 24:15 - Andrew Ng's Landing AI raises 57M 25:40 - Cerebras raises 250M 26:45 - Microsoft's Varuna: Scalable Training of Huge Models 28:15 - Laura Ruis reproduces Extrapolation Paper 29:05 - Ian Charnas' Real-Life Punchout 30:00 - Helpful Things 33:10 - AI finds profitable Meme-Tokens 34:55 - This Sneaker Does Not Exist Sponsor: Weights & Biases https://wandb.com References: Cedille - French Language Model https://en.cedille.ai/ https://ift.tt/3H85Zwp https://app.cedille.ai/ https://ift.tt/30CyvFz Facebook AI Multilingual model wins WMT https://ift.tt/3kmAPHN YOU private search engine https://you.com/ https://ift.tt/3nuX5l4 DeepMind's Open-Source Arnheim https://ift.tt/2YXQPIU https://twitter.com/OriolVinyalsML/status/1459231774068854785 https://ift.tt/3crORna https://ift.tt/32dSbRc Company sued for using AI to make website more accessible https://ift.tt/3F7IhPe https://ift.tt/30KgJAJ Alibaba DAMO Academy creates 10 Trillion M6 model https://ift.tt/31CeKyx https://ift.tt/30y7N0X AMD MI200 Family https://ift.tt/3kJUGkw State of AI report 2021 https://ift.tt/3HBcFDo Andrew Ng's Landing AI raises 57M https://ift.tt/3wp5aKG https://ift.tt/3wvHdkR https://ift.tt/3nqA02S Cerebras raises 250M https://ift.tt/30EqOiA https://ift.tt/3wYO5HO Microsoft's Varuna: Scalable Training of Huge Models https://ift.tt/3EYHWy0 Laura Ruis reproduces Extrapolation Paper https://ift.tt/3CxnYZE https://ift.tt/3nsDpho Ian Charnas' Real-Life Punchout https://ift.tt/3o7FCxV https://www.youtube.com/watch?v=07JibJJVNp8 Helpful Things https://ift.tt/3k7IGJ9 https://ift.tt/3DvEPNW https://ift.tt/3kJeYcu https://ift.tt/3DdMUXs https://twitter.com/yeemachine/status/1457779633449934848?utm_source=pocket_mylist https://ift.tt/3C5jKIM AI finds profitable Meme-Tokens https://ift.tt/3CbiweZ https://finu.co/ This Sneaker Does Not Exist https://ift.tt/3mIJnZX Links: TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ift.tt/3dJpBrR BitChute: https://ift.tt/38iX6OV LinkedIn: https://ift.tt/3qcgOFy BiliBili: https://ift.tt/3nlqFZS If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://ift.tt/2DuKOZ3 Patreon: https://ift.tt/390ewRH Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

Wednesday, November 17, 2021

Detectron2 Panoptic Segmentation Demo

#Detectron2 #PanopticSegmentation #InstanceSegmentation #ComputerVision #ObjectDetection #RaspberryPi #GoPro #AI #MachineLearning #Tutorial #ScienceandTechnology #ArtificialIntelligence #VertexAI #AIServing #AIDeployment **This video is best viewed with the 1080p60 HD setting In this video we demonstrate using Detectron2 to perform Object Detection, Instance Segmentation and Panoptic Segmentation on a sample image and video. Here is the list of topics explained in this video: 1. Detectron2 - What is it? - (0:33) 2. Topics in this Demo - (0:55) 3. Open a Google colaboratory notebook - (1:14) 4. Run first cell in Detectron2 Google colaboratory notebook - (3:05) 5. Import sample image - (4:17) 6. Object detection on a sample image - (5:02) 7. Instance Segmentation on a sample image - (6:39) 8. Panoptic Segmentation on a sample image - (8:13) 9. Panoptic Segmentation on a sample video clip - (9:33) 10. Panoptic Segmentation sample video clip output results - (12:26) GitHub Google Colaboratory notebooks https://github.com/BlackMagicAI/Detectron2-Demo Original Detectron2 Github notebooks https://github.com/facebookresearch/detectron2 Google Colaboratory Introduction videos Introduction to Google Colaboratory - AI & Machine Learning Workshop - Part 4 (https://youtu.be/y7_UTqwx5Y0) XOR ML Example - AI & Machine Learning Workshop - Part 8 (https://youtu.be/I_Xuwa9tHZk) Previous Computer Vision Object detection videos Tiny-Yolo 3 on a Raspberry Pi using a GoPro Camera (https://youtu.be/jwgcDGFyXIY) Tiny-Yolo 3 on the Raspberry Pi (https://youtu.be/SWrTS63zgoU) Like/follow us on Facebook: https://www.facebook.com/Black-Magic-AI-109126344070229 Check out our Web site: https://www.blackmagicai.com/ Background Music Royalty Free background music from Bensound.com.

Outliers | Probability and Statistics For Machine Learning

CDF(Cumulative Distribution Function) | Probability and Statistics For Machine Learning

BASIC INPUT/OUTPUT I/O IN TEXT FILE | VARIOUS MODE OF OPENING TEXT FILE IN PYTHON | VIDEO 13

Anaconda, Python, Machine Learning & AI Code - 100 Day Challenge Day #3

Tuesday, November 16, 2021

(ASE'21 Tutorial) Explainable AI for Software Engineering

Slide: https://speakerdeck.com/klainfo/c18f1166-d90c-4d5a-96ef-07b79fe157ad Materials: http://xai4se.github.io The success of software engineering projects largely depends on complex decision-making. For example, which tasks should a developer do first, who should perform this task, is the software of high quality, is a software system reliable and resilient enough to deploy, etc. However, erroneous decision-making for these complex questions is costly in terms of money and reputation. Thus, Artificial Intelligence/Machine Learning (AI/ML) techniques have been widely used in software engineering for developing software analytics tools and techniques to improve decision-making, developer productivity, and software quality. However, the predictions of such AI/ML models for software engineering are still not practical (i.e., fine-grained), not explainable, and not actionable. These concerns often hinder the adoption of AI/ML models in software engineering practices. In addition, many recent studies still focus on improving the accuracy, while a few of them focus on improving explainability. Are we moving in the right direction? How can we better improve the SE community (both research and education)? In this book, we first provide a concise yet essential introduction to the most important aspects of Explainable AI and a hands-on tutorial of Explainable AI tools and techniques. Then, we introduce the fundamental knowledge of defect prediction (an example application of AI for Software Engineering). Finally, we demonstrate three successful case studies on how Explainable AI techniques can be used to address the aforementioned challenges by making the predictions of software defect prediction models more practical, explainable, and actionable.

Detectron2 Panoptic Segmentation Demo

New AI: Photos Go In, Reality Comes Out! 🌁

❤️ Check out Lambda here and sign up for their GPU Cloud: https://ift.tt/35NkCT7 📝 The paper "ADOP: Approximate Differentiable One-Pixel Point Rendering" is available here: https://ift.tt/2YPGHlE ❤️ Watch these videos in early access on our Patreon page or join us here on YouTube: - https://ift.tt/2icTBUb - https://www.youtube.com/channel/UCbfYPyITQ-7l4upoX8nvctg/join 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Aleksandr Mashrabov, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Benji Rabhan, Bryan Learn, Christian Ahlin, Eric Martel, Gordon Child, Ivo Galic, Jace O'Brien, Javier Bustamante, John Le, Jonas, Kenneth Davis, Klaus Busse, Lorin Atzberger, Lukas Biewald, Matthew Allen Fisher, Mark Oates, Michael Albrecht, Michael Tedder, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Rajarshi Nigam, Ramsey Elbasheer, Steef, Taras Bobrovytsky, Thomas Krcmar, Timothy Sum Hon Mun, Torsten Reil, Tybie Fitzhugh, Ueli Gallizzi. If you wish to appear here or pick up other perks, click here: https://ift.tt/2icTBUb Thumbnail background design: Felícia Zsolnai-Fehér - http://felicia.hu Meet and discuss your ideas with other Fellow Scholars on the Two Minute Papers Discord: https://ift.tt/2TnVBd3 Károly Zsolnai-Fehér's links: Instagram: https://ift.tt/2KBCNkT Twitter: https://twitter.com/twominutepapers Web: https://ift.tt/1NwkG9m

Monday, November 15, 2021

Gradients are Not All You Need (Machine Learning Research Paper Explained)

#deeplearning #backpropagation #simulation More and more systems are made differentiable, which means that accurate gradients of these systems' dynamics can be computed exactly. While this development has led to a lot of advances, there are also distinct situations where backpropagation can be a very bad idea. This paper characterizes a few such systems in the domain of iterated dynamical systems, often including some source of stochasticity, resulting in chaotic behavior. In these systems, it is often better to use black-box estimators for gradients than computing them exactly. OUTLINE: 0:00 - Foreword 1:15 - Intro & Overview 3:40 - Backpropagation through iterated systems 12:10 - Connection to the spectrum of the Jacobian 15:35 - The Reparameterization Trick 21:30 - Problems of reparameterization 26:35 - Example 1: Policy Learning in Simulation 33:05 - Example 2: Meta-Learning Optimizers 36:15 - Example 3: Disk packing 37:45 - Analysis of Jacobians 40:20 - What can be done? 45:40 - Just use Black-Box methods Paper: https://ift.tt/3n6RwsR Abstract: Differentiable programming techniques are widely used in the community and are responsible for the machine learning renaissance of the past several decades. While these methods are powerful, they have limits. In this short report, we discuss a common chaos based failure mode which appears in a variety of differentiable circumstances, ranging from recurrent neural networks and numerical physics simulation to training learned optimizers. We trace this failure to the spectrum of the Jacobian of the system under study, and provide criteria for when a practitioner might expect this failure to spoil their differentiation based optimization algorithms. Authors: Luke Metz, C. Daniel Freeman, Samuel S. Schoenholz, Tal Kachman Links: TabNine Code Completion (Referral): http://bit.ly/tabnine-yannick YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher Discord: https://ift.tt/3dJpBrR BitChute: https://ift.tt/38iX6OV LinkedIn: https://ift.tt/3qcgOFy BiliBili: https://ift.tt/3nlqFZS If you want to support me, the best thing to do is to share out the content :) If you want to support me financially (completely optional and voluntary, but a lot of people have asked for this): SubscribeStar: https://ift.tt/2DuKOZ3 Patreon: https://ift.tt/390ewRH Bitcoin (BTC): bc1q49lsw3q325tr58ygf8sudx2dqfguclvngvy2cq Ethereum (ETH): 0x7ad3513E3B8f66799f507Aa7874b1B0eBC7F85e2 Litecoin (LTC): LQW2TRyKYetVC8WjFkhpPhtpbDM4Vw7r9m Monero (XMR): 4ACL8AGrEo5hAir8A9CeVrW8pEauWvnp1WnSDZxW7tziCDLhZAGsgzhRQABDnFy8yuM9fWJDviJPHKRjV4FWt19CJZN9D4n

(ASE'21 Tutorial) Explainable AI for Software Engineering

Friday, November 12, 2021

Incredible things your community is creating with TensorFlow.js - Made with TensorFlow.js

Usage of Machine Learning in JavaScript has grown exponentially since 2020 and is expected to continue. Check out just a few of our community highlights to see what people are making from all around the world. From self driving cars to motion captured avatars, we have it all, and it runs with a single click in the browser and beyond. Get more eyes on your research with TensorFlow.js. Resources: Watch more #MadeWithTFJS → https://goo.gle/3H4aB6U Show & Tell on the TensorFlow Forum → https://goo.gle/3bQKstE Speaker: Jason Mayes Watch all Google's Machine Learning Virtual Community Day sessions → https://goo.gle/mlcommunityday-all Subscribe to the TensorFlow channel → https://goo.gle/TensorFlow #MLCommunityDay product: TensorFlow - General; event: ML Community Day 2021; fullname: Jason Mayes; re_ty: Publish;

How to get involved in Machine Learning

Whether you're just getting started with Machine Learning or want to scale your business using ML, there are many ways to get involved in the ML community. Learn how to contribute to the TensorFlow ecosystem and be an active member in our community. Speaker: Joana Carrasqueira Watch all Google's Machine Learning Virtual Community Day sessions → https://goo.gle/mlcommunityday-all Subscribe to the TensorFlow channel → https://goo.gle/TensorFlow #MLCommunityDay product: TensorFlow - General; event: ML Community Day 2021; fullname: Joana Carrasqueira; re_ty: Publish;