Bookmarks

Bookmarks Bar
DL Articles 6 areas of AI&ML to watch (come back to this routinely) What a Deep Neural Network thinks about your #selfie Neuron explained using simple algebra – Chingu – Medium ML is Fun (World's easiest intro to ML) Identifying rare diseases, lung cancer & more with Deep Learning – Transmission Newsletter – Medium An overview of gradient descent optimization algorithms Write an AI to win at Pong from scratch with Reinforcement Learning – Medium Artificial Intelligence, Deep Learning, and Neural Networks, Explained Deep Neural Networks Are Easily Fooled: High Confidence Predictions for Unrecognizable Images Beginner's Guide To Convolutional Neural Networks – Adit Deshpande – CS Undergrad at UCLA ('19) Books AdvBk: Deep Learning (Ian Goodfellow) IntroBk: NN and DL (M. Nielsen) COURSE TEXTBOOK: Manning | Grokking Deep Learning Competitions Bag of Words Meets Bags of Popcorn | Kaggle CNNs 2014: Olah: Conv Nets: A Modular Perspective 2012: Krizhevsky et al: ImageNet classification w/ deep CNNs Convolution Animations ConvNetJS demo: Classify toy 2D data Understanding Convolutions - colah's blog Understanding Convolutional Neural Networks for NLP – WildML Convolutional Neural Networks (LeNet) Visualizing and Understanding CNNs 2014: Lin et al: Network in Network (1x1 Convolutions) 2014: Szegedy et al: Going deeper w/ convolutions (Google) Courses OpenAI Gym bayareadlschool | presentations Sutton & Barto Book: Reinforcement Learning: An Introduction John Schulman: Deep Reinforcement Learning (YouTube) Udacity__DL-NDF Udacity-DL NanoDegree Main Page Syllabus Overview (blog) Udacity-DL Slack UdacityDL Forums Udacity-DL Student Handbook A Neural Network Playground An overview of ... Momentum Google TensorFlow Series Live Q&A with the Deep Learning Foundations Team - YouTube How to Use Tensorflow for Time Series (Live) - YouTube MIT Self-Driving Car DeepTesla Tutorial GitHub - lexfridman/deeptesla DeepTraffic Udacity__Intro-to-DL Take this 1st: DL cs231n: CNNs for VizRec 2016 Main Page 2016 Notes on GitHub UCL Course on Reinforcement Learning (2015) 2015: Machine Learning (DL, CNN, RNN, RL, etc) 2017: UCB-cs294: Deep Reinforcement Learning 2015: UCB-cs294: Deep Reinforcement Learning (abbv version of 2017 course) Quoc Le’s Lectures on Deep Learning TensorFlow and deep learning, without a PhD Practical tutorials and labs for TensorFlow used by Nvidia, FFN, CNN, RNN, Kaggle, AE Watch this: Ng Overview of DL Rec: Intro to Comp Vision Rec: AI for Robotics Stanford: ConvNN for Visual Recognition Stat212b: Topics Course on Deep Learning by joanbruna Neural Networks for Machine Learning - University of Toronto | Coursera CS231n Convolutional Neural Networks for Visual Recognition CS231n Winter 2016 - YouTube CS 294 Deep Reinforcement Learning, Spring 2017 DataNews The Wild Week in AI DeepLearning.Net Transmission Newsletter – Medium DataTau (ML/DL News) Deep Learning Weekly DataSets MNIST SVHN (Street View House Numbers) CIFAR-10 and CIFAR-100 de/trans CNNs 2010: Zeiler et al (NYU): Deconvolutional Networks Zeiler's Slides on Deconvolutional Networks CS231n Winter 2016: Lecture 13: Segmentation, soft attention, spatial transformers - YouTube What are deconvolutional layers? (Stack Exchange) GANs [1406.2661] Generative Adversarial Networks [1606.03498] Improved Techniques for Training GANs openai/improved-gan: code for the paper "Improved Techniques for Training GANs" [1606.03657] InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets openai/InfoGAN Newmu/dcgan_code: Deep Convolutional Generative Adversarial Networks [1606.03476] Generative Adversarial Imitation Learning openai/imitation Hardware NVIDIA TITAN X Graphics Card with Pascal (what OpenAI uses) Andrew's Linux Rig Build a super fast deep learning machine for under $1,000 - O'Reilly Media Home Pages Bengio Home Page Andrej Karpathy Home Page Richard Socher - Home Page Greg Brockman (@gdb) | Twitter Ilya Sutskever's home page Trevor Blackwell | Home Page Diederik P. Kingma | Home Page John Schulman's Homepage Hugo Larochelle | Home Page Wojciech Zaremba | Home Page Adam Coates PhD Dissertation Home - colah's blog Kernel Methods for DL 2009: Cho: Kernel Methods for Deep Learning 2011: Montavon: Kernel Analysis of Deep Networks NLP Word2Vec & Friends (YouTube) 2013: Mikolov et al: Efficient Estimation of Word Representations in Vector Space (Word2Vec) 2014: Goldberg & Levy: word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method Word2vec - Wikipedia Word embedding - Wikipedia 2014: Olah: Deep Learning, NLP, and Representations 2010: Turian et al: Word Representations: A simple and general method for semi-supervised learning 2001: Bengio et al: A Neural Probabilistic Language Model - LISA - Publications - Aigaion 2.0 2003: Bengio et al: A Neural Probabilistic Language Model 2013: Luong et al: Better word representations w/ RNNs for Morphology (pdf) 2014: Norouzi et al: Zero-shot learning by convex combination of semantic embeddings 2011: Collobert et al: NLP (almost) from Scratch Standford Course: Deep Learning for NLP Stanford Course: NLP with Deep Learning (most recent) 2013: Mikolov et al: Linguistic Regularities in Continuous Space Word Representations 2014: Hannun et al: Deep Speech: Scaling up end-to-end speech recognition 2015: Amodei et al: Deep Speech 2: End-to-End Speech Recognition in English and Mandarin [1611.04558] Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation Lexicon-Based Methods for Sentiment Analysis Sentiment Analysis w/ Deeply Learned Distributed Representations of Variable Length Texts Distributed Representations of Sentences and Documents LSTM Networks for Sentiment Analysis OpenAI OpenAI Gym Ant-v1 OpenAI Gym: Documentation Humanoid-v1 Blog Requests for Research Jobs at OpenAI Gaming Environments OpenAI Forum NIPS 2016 OpenAI Schedule openai/universe-starter-agent Inside OpenAI, Elon Musk’s Wild Plan to Set Artificial Intelligence Free | WIRED Q/Reinforcement Learning Deep Reinforcement Learning: Pong from Pixels UCL Course on Reinforcement Learning [1605.09674] VIME: Variational Information Maximizing Exploration openai/vime Quasi-RNNs 2016: Bradbury et al: Quasi-Recurrent Neural Networks RecEngPapers Proceedings of the RecSys 2011 Workshop on Human Decision Making in Recommender Systems (Decisions@RecSys’11) and User‐Centric Evaluation of Recommender Systems and Their Interfaces ‐ 2 (UCERSTI 2) affiliated with the 5th ACM Conference on Recommend download a13-gomez-uribe.pdf bingham-walker.pdf Conference_UMAP_2016_re.pdf SIG-039-Perfect.indd 1409.2944.pdf End-to-end learning for music audio Improving Content-based and Hybrid Music Recommendation using Deep Learning Piczak2015-ESC-ConvNet.pdf Analyzing Spotify Data Workshop_RSWEB_2014.pdf FIVE_APPROACHES_TO_COLLECTING_TAGS_FOR_MUSIC_ISMIR08.pdf Gomez-Uribe: The Netflix recommender system: Algorithms,... - Google Scholar Relations to Physics Path Integrals of Information (pdf) Path integral guided policy search A neural network wave formalism - ScienceDirect What are the connections between machine learning and physics? - Quora Deep Learning Relies on Renormalization, Physicists Find | Quanta Magazine Why Deep Learning Works II: the Renormalization Group – CALCULATED CONTENT Understanding Convolution in Deep Learning (It's all fluid dynamics, QM, etc) machine learning - Why the sudden fascination with tensors? - Cross Validated Neural Networks, Manifolds, and Topology Paper: Why does deep/cheap learning work so well? (Lin&Tegmark2016) [1410.3831] An exact mapping between the Variational Renormalization Group and Deep Learning RNNs Understanding LSTM Networks The Unreasonable Effectiveness of Recurrent Neural Networks 1994: Bengio et al: Learning long-term dependencies with gradient descent is difficult (synopsis: why standard RNNs are good in theory, but suck in practice) 1997: Hochreiter & Schmidhuber: Long Short-term Memory (i.e., the new, non-sucky RNN) 2016: Olah & Carter: Attention and Augmented Recurrent Neural Networks [1601.06759] Pixel Recurrent Neural Networks Exploring the Limits of Language Modeling CS231n Lecture 10 - Recurrent Neural Networks, Image Captioning, LSTM - YouTube DLBook: Ch10: Sequence Modeling w/ Recurrent and Recursive Nets 1997: Hochreiter & Schmidhuber: Long Short-Term Memory 1999: Gers, Schmidhuber & Cummins: Learning to Forget 2008: Graves: Supervised Sequence Labelling w/ RNNs (Dissertation) A Critical Review of RNNs for Sequence Learning 2016: Karpathy, Johson, Fei-Fei: Visualizing and Understanding RNNs Written Memories: Understanding, Deriving and Extending the LSTM - R2RT Style Transfer A Neural Algorithm of Artistic Style Perceptual Losses for Real-Time Style Transfer and Super-Resolution Instance Normalization GitHub - lengstrom/fast-style-transfer: Fast Style Transfer in TensorFlow! ⚡🖥🎨🖼 Fast Style Transfer Models - Google Drive VAEs High-Level Explanation of Variational Inference Blei2004.pdf [1505.05770] Variational Inference with Normalizing Flows [1312.6114] Auto-Encoding Variational Bayes [1502.04623] DRAW: A Recurrent Neural Network For Image Generation [1603.08575] Attend, Infer, Repeat: Fast Scene Understanding with Generative Models 2011: Rifai et al: Contractive Auto-Encoders: Explicit Invariance During Feature Extraction Exponential expressivity in deep neural networks through transient chaos (PDF) SOMs SOM: Fundamentals (from jxb notes) SOMs: Algorithms & Applications (from jxb notes) SOM tutorial part 1 Self-organizing map - Wikipedia Self-Organizing Maps with Google’s TensorFlow | Sachin Joglekar's blog Scale/Rot-Inv DL 2014: Kanazawa et al: Locally Scale-Invariant Convolutional Neural Networks Quantifying translation-invariance in CNNs 2016: Marcos et al: Learning rotation invariant convolutional filters for texture classification Encoded invariance in CNNs Rotation-invariant neoperceptron akanazawa/si-convnet: Implementation of the [Locally Scale-Invariant Convolutional Neural Network](http://www.umiacs.umd.edu/~kanazawa/papers/sicnn_workshop2014.pdf) Transform-Invariant Convolutional Neural Networks for Image Classification and Search 2016: Duvenaud: Avoiding pathologies in very deep networks 2013: Szegedy et al: Intriguing properties of neural networks Can you beat a computer? (Karpathy's image test) Google Translate Amazon Mechanical Turk CrowdFlower (AI for your Biz) Project Malmo (Microsoft) TensorBoard MS COCO (Common Objects in Context) Gab41 WildML – AI, Deep Learning, NLP ConvNetJS Deep Q Demo ConvNetJS: Deep Learning in your browser Google's ML Style Guide DL (small review paper: LeCun, Bengio, & Hinton) List of Most-Cited DL/ML papers Floyd Zero Setup Deep Learning Dropout: A Simple Way to Prevent NNs from Overfitting [0908.4425] Geometry of the restricted Boltzmann machine Practical Guide to Training Restricted Boltzmann Machines Recommending music on Spotify with deep learning – Sander Dieleman