rajeshkumargp/machine-learning-resources

List of books and other resources that are related to deep learning

Machine Learning Resources

This is a curated list of resources that I have found useful regarding machine learning, in particular deep learning. Only books that add significant value to understanding the topic are listed. Also, a list of good articles and some other resources.

Background

• Introduction to Mathematical Statistics
  Robert Hogg, Joeseph McKean and Allen Craig

• Numerical Linear Algebra and Applications
  Biswa Nath Datta

Introductory

• Introduction To Machine Learning
  Ethem Alpaydin

Advanced

• Reinforcement Learning: An Introduction
  Richard Sutton and Andrew Barto

• The Elements of Statistical Learning
  Trevor Hastie, Robert Tibshirani and Jerome Friedman

• Pattern Recognition and Machine Learning
  Christopher Bishop

• Machine Learning: A Probabilistic Perspective
  Kevin Murphy

Deep Learning Specific

• Deep Learning
  Ian Goodfellow, Yoshua Bengio and Aaron Courville

• Deep Learning with Python
  François Chollet

Background Literature

• Variational Inference: A Review for Statisticians

Interesting and Relevant Articles

• HELIX: Accelerating Human-in-the-loop Machine Learning

• Distributional Multivariate Policy Evaluation and Exploration with the Bellman GAN

• Predicting Acute Kidney Injury at Hospital Re-entry Using High-dimensional Electronic Health Record Data

• Hidden Technical Debt in Machine Learning Systems

• Online Adaptative Curriculum Learning for GANs

• GuiTeNet: A graphical user interface for tensor networks

• Speaker Recognition from Raw Waveform with Sincnet

• Blind Justice: Fairness with Encrypted Sensitive Attributes

• Neural Joking Machine: Humorous image captioning

• Neural Arithmetic Logic Units

• Rank and Rate: Multi-task Learning for Recommender Systems

• DeepProbLog: Neural Probabilistic Logic Programming

• YOLO Net on iOS

• TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing

• The challenge of realistic music generation: modelling raw audio at scale

• Meta-learning autoencoders for few-shot prediction

• Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes

• Discovering physical concepts with neural networks

• Painting Outside the Box: Image Outpainting with GANs

• Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer

• Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors

• Representation Learning with Contrastive Predictive Coding

• Variational Memory Encoder-Decoder

• The Variational Homoencoder: Learning to learn high capacity generative models from few examples

• Implementing Neural Turing Machines

• DARTS: Differentiable Architecture Search

• Variational Bayesian Reinforcement Learning with Regret Bounds

• Backprop-Q: Generalized Backpropagation for Stochastic Computation Graphs

• Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model

• Compositional GAN: Learning Conditional Image Composition

• Adversarial Reprogramming of Neural Networks

• CNN Features off-the-shelf: an Astounding Baseline for Recognition

• Neural Motifs: Scene Graph Parsing with Global Context

• Multitask Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies

• Glow: Generative Flow with Invertible 1×1 Convolutions

• Noise2Noise: Learning Image Restoration without Clean Data

• Representation Learning with Contrastive Predictive Coding

• An Opinionated Introduction to AutoML and Neural Architecture Search

• ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo Systems

• IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis

• Backplay: ‘Man muss immer umkehren’

• Meta-Learning With Latent Embedding Optimization

• TequilaGAN: How to easily identify GAN samples

• The Singular Values of Convolutional Layers

• TherML: Thermodynamics of Machine Learning

• Variance Networks: When Expectation Does Not Meet Your Expectations

• Task-Driven Convolutional Recurrent Models of the Visual System

• Beyond Winning and Losing: Modeling Human Motivations and Behaviors Using Inverse Reinforcement Learning

• Deep Neural Networks as Gaussian Processes

• Co-Training of Audio and Video Representations from Self-Supervised Temporal Synchronization

• Dynamic Integration of Background Knowledge in Neural NLU Systems

• The relativistic discriminator: a key element missing from standard GAN

• Accurate Uncertainties for Deep Learning Using Calibrated Regression

• ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotations

• The challenge of realistic music generation: modelling raw audio at scale

• Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding

• Tracking Emerges by Colorizing Videos

• Probabilistic FastText for Multi-Sense Word Embeddings

• Differentiable Compositional Kernel Learning for Gaussian Processes

• Learning Dynamics of Linear Denoising Autoencoders

• Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks

• Bilinear Attention Networks

• Global Pose Estimation with an Attention-based Recurrent Network

• SparseMAP: Differentiable Sparse Structured Inference

• Neural Ordinary Differential Equations

• Zero-Shot Visual Imitation

• Multimodal Unsupervised Image-to-Image Translation

• Deep Painterly Harmonization

• A Probabilistic U-Net for Segmentation of Ambiguous Images

• DeViSE: A Deep Visual-Semantic Embedding Model

• Through-Wall Human Pose Estimation Using Radio Signals

• Adversarial Meta-Learning

• Fighting Fake News: Image Splice Detection via Learned Self-Consistency

• GAN Q-learning

• A Simple Method for Commonsense Reasoning

• Semi-supervised Sequence Learning

• Deep learning models reveal internal structure and diverse computations in the retina under natural scenes

• Learning New Physics from a Machine

• Spectral Inference Networks: Unifying Spectral Methods With Deep Learning

• Probabilistic Model-Agnostic Meta-Learning

• Granger-causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks

• Relational inductive biases, deep learning, and graph networks

• DetNet: A Backbone network for Object Detection

• Playing Atari with Six Neurons

• Multi-Resolution 3D Convolutional Neural Networks for Object Recognition

• Do CIFAR-10 Classifiers Generalize to CIFAR-10?

• Supervised Open Information Extraction

• Learning a Latent Space of Multitrack Measures

• Structure from noise: Mental errors yield abstract represen- tations of events

• Learning to Extract Coherent Summary via Deep Reinforcement Learning

• MolGAN: An implicit generative model for small molecular graphs

• Approximate Random Dropout

• Variational Inference for Data-Efficient Model Learning in POMDPs

• Learning a Prior over Intent via Meta-Inverse Reinforcement Learning

• Neural Discrete Representation Learning

• Aggregated Residual Transformations for Deep Neural Networks

• Playing hard exploration games by watching YouTube

• Capsules for Object Segmentation

• Learning to Transduce with Unbounded Memory

• Visceral Machines: Reinforcement Learning with Intrinsic Rewards that Mimic the Human Nervous System

• Neural Collaborative Filtering

• Altered Fingerprints: Detection and Localization

• Fast animal pose estimation using deep neural networks

• DOOM Level Generation using Generative Adversarial Networks

• Pixel Recurrent Neural Networks

• Solving the Rubik’s Cube Without Human Knowledge

• Adding One Neuron Can Eliminate All Bad Local Minima

• Synthesizing Images of Humans in Unseen Poses

• Depth-Limited Solving for Imperfect-Information Games

• AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search

• Semantic Autoencoder for Zero-shot Learning

• Progress & Compress: A scalable framework for continual learning

• Regularization Learning Networks

• On the Practical Computational Power of Finite Precision RNNs for Language Recognition

• Learning Intrinsic Image Decomposition from Watching the World

• Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images

• Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond

• Learning Intrinsic Image Decomposition from Watching the World

• Time Series Epenthesis: Clustering Time Series Streams Requires Ignoring Some Data

• Realistic Evaluation of Semi-Supervised Learning Algorithms

• Multiclass Transfer Learning from Unconstrained Priors

• Multi-column Deep Neural Networks for Image Classification

• Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks

• A Unified Framework of Deep Neural Networks by Capsules

• Learning to Separate Object Sounds by Watching Unlabeled Video

• Bayesian Robust Tensor Factorization for Incomplete Multiway Data

• Quantization Mimic: Towards Very Tiny CNN for Object Detection

• Efficient Convolutional Network Learning using Parametric Log based Dual-Tree Wavelet ScatterNet

• Real-time Semantic Segmentation of Crop and Weed for Precision Agriculture Robots Leveraging Background Knowledge in CNNs

• Sim-to-Real: Learning Agile Locomotion For Quadruped Robots

• Capsule networks for low-data transfer learning

• Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs

• Towards Symbolic Reinforcement Learning with Common Sense

• Compositional Attention Networks for Machine Reasoning

• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

• Multiagent Soft Q-Learning

• Convergence of Value Aggregation for Imitation Learning

• Why does deep and cheap learning work so well?

• node2vec: Scalable Feature Learning for Networks

• Realistic Evaluation of Deep Semi-Supervised Learning Algorithms

• Activity Detection with Latent Sub-event Hierarchy Learning

• Variational Knowledge Graph Reasoning

• Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation

• MergeNet: A Deep Net Architecture for Small Obstacle Discovery

• Harmonic Networks: Deep Translation and Rotation Equivariance

• ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing

• Deep Object Co-Segmentation

• Detecting Malicious PowerShell Commands using Deep Neural Networks

• Multimodal Unsupervised Image-to-Image Translation

• Regularizing Deep Networks by Modeling and Predicting Label Structure

• Recurrent Recommender Networks

• Generative Adversarial Networks for Extreme Learned Image Compression

• Concept2vec: Metrics for Evaluating Quality of Embeddings for Ontological Concepts

• Neural Aesthetic Image Reviewer

• Manifold Alignment

• A General Framework for Manifold Alignment

• Differentiable plasticity: training plastic neural networks with backpropagation

• Spatial Graph Convolutions for Drug Discovery

• sense2vec - A Fast and Accurate Method for Word Sense Disambiguation In Neural Word Embeddings

• Algebraic Machine Learning

• Network In Network

• Neural Voice Cloning with a Few Samples

• L4: Practical loss-based stepsize adaptation for deep learning

• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

• Complex-YOLO: An Euler-Region-Proposal for Real-time 3D Object Detection on Point Clouds

• code2vec: Learning Distributed Representations of Code

• Human Semantic Parsing for Person Re-identification

• Group Normalization

• Some Theoretical Properties of GANs

• Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings

• Deep Spatial Pyramid for Person Re-identification

• Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval

• Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning

• Simple random search provides a competitive approach to reinforcement learning

• ChatPainter: Improving Text to Image Generation using Dialogue

• Deep Metric Learning with Angular Loss

• Deep Metric Learning via Lifted Structured Feature Embedding

• Hard Negative Mining for Metric Learning Based Zero-Shot Classification

• Triplet-based Deep Similarity Learning for Person Re-Identification

• How to Train Triplet Networks with 100K Identities?

• Deep Metric Learning Using Triplet Network

• Robust Monitoring of Time Series with Application to Fraud Detection

• Neural Machine Translation by Jointly Learning to Align and Translate

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

• Sequence to Sequence Learning with Neural Networks

• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings

• Extracting Domain Invariant Features By Unsupervised Learning For Robust Automatic Speech Recognition

• Compositional Attention Networks For Machine Reasoning

• Kickstarting Deep Reinforcement Learning

• Learning a Parametric Embedding by Preserving Local Structure

• Unsupervised Document Embedding With CNNs

• Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives

• Advances in Variational Inference

• Evolutionary Generative Adversarial Networks

• Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions

• The Building Blocks of Interpretability

• End-to-end Deep Image Reconstruction From Human Brain Activity

• TSSD: Temporal Single-Shot Detector Based on Attention and LSTM for Robotic Intelligent Perception

• Brain Tumor Type Classification via Capsule Networks

• Recent Advances in Recurrent Neural Networks

• Bayesian Inverse Reinforcement Learning

• Generative Adversarial Text to Image Synthesis

• One Big Net For Everything

• Deep Multimodal Learning For Emotion Recognition In Spoken Language

• A Neural Parametric Singing Synthesizer

• On Characterizing the Capacity of Neural Networks using Algebraic Topology

• Adversarial Examples that Fool both Human and Computer Vision

• Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

• Deep Networks with Stochastic Depth

• Wide Residual Networks

• Tiny SSD: A Tiny Single-shot Detection Deep Convolutional Neural Network for Real-time Embedded Object Detection

• Supervised Dimensionality Reduction via Distance Correlation Maximization

• Faster gaze prediction with dense networks and Fisher pruning

• Classification and clustering for samples of event time data using non-homogeneous Poisson process models

• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

• Countering Adversarial Images Using Input Transformations

• The Matrix Calculus You Need For Deep Learning

• Deep Temporal Clustering : Fully Unsupervised Learning of Time-Domain Features

• Regularized Evolution for Image Classifier Architecture Search

• Quasi-Recurrent Neural Networks

• From Micro to Macro: Data Driven Phenotyping by Densification of Longitudinal Electronic Medical Records

• Speed/accuracy trade-offs for modern convolutional object detectors

• Nested LSTMs

• Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks

• Audio Adversarial Examples: Targeted Attacks on Speech-to-Text

• Deep Multi-Camera People Detection

• Learning to Segment Every Thing

• ComboGAN: Unrestrained Scalability for Image Domain Translation

• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

• Understanding deep learning requires rethinking generalization

• Bayesian GAN

• Approximations by superpositions of sigmoidal functions

• Are GANs Created Equal? A Large-Scale Study

• Learning to Segment Every Thing

• A Neural Algorithm of Artistic Style

• VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

• Generalization in Deep Learning

• DeepFace: Closing the Gap to Human-Level Performance in Face Verification

• Feature Space Optimization for Semantic Video Segmentation

• Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes

• Pyramid Scene Parsing Network

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

• Fast R-CNN

• Rich feature hierarchies for accurate object detection and semantic segmentation

• Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

• Exploit All the Layers: Fast and Accurate CNN Object Detector with Scale Dependent Pooling and Cascaded Rejection Classifiers

• Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks

• 3D Object Proposals using Stereo Imagery for Accurate Object Class Detection

• Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

• The Cityscapes Dataset for Semantic Urban Scene Understanding

• Superpixel Convolutional Networks Using Bilateral Inceptions

• Aggressive Deep Driving: Combining Convolutional Neural Networks and Model Predictive Control

• Multi-View 3D Object Detection Network for Autonomous Driving

• High-Resolution Semantic Labeling with Convolutional Neural Networks

• InstanceCut: from Edges to Instances with MultiCut

• End to End Learning for Self-Driving Cars

• Instance-aware Semantic Segmentation via Multi-task Network Cascades

• Globally and Locally Consistent Image Completion

• Vehicle Detection from 3D Lidar Using Fully Convolutional Network

• The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes

• Synthesizing Robust Adversarial Examples

• OctNet: Learning Deep 3D Representations at High Resolutions

• EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis

• Hierarchical Representations for Efficient Architecture Search

• Squeeze-and-Excitation Networks

• Improving Deep Learning by Inverse Square Root Linear Units (ISRLUs)

• Long Short-Term Memory as a Dynamically Computed Element-wise Weighted Sum

• Deformable Convolutional Networks

• Soft-NMS -- Improving Object Detection With One Line of Code

• A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection

• SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

• Incremental Dense Semantic Stereo Fusion for Large-Scale Semantic Scene Reconstruction

• Dynamic Routing Between Capsules

• StixelNet: A Deep Convolutional Network for Obstacle Detection and Road Segmentation

• Semantic Image Segmentation with Deep Cconvolutional Nets and Fully Connected CRFS

• A New Artificial Neural Network Approach in Solving Inverse Kinematics of Robotic Arm (Denso VP6242)

• Hands Deep in Deep Learning for Hand Pose Estimation

• Auto-Conditioned LSTM Network for Extended Complex Human Motion Synthesis

• DeepXplore: Automated Whitebox Testing of Deep Learning Systems

• Orientation-boosted Voxel Nets for 3D Object Recognition

• Real-time grasp detection using convolutional neural networks

• On the difficulty of training Recurrent Neural Networks

• Learning real manipulation tasks from virtual demonstrations using LSTM

• A Neural Network-Based Approach for Trajectory Planning in Robot–Human Handover Tasks

• Swish: a Self-Gated Activation Function

• SE3-Nets: Learning Rigid Body Motion using Deep Neural Networks

• Visual Servoing from Deep Neural Networks

• UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning

• Deep 6-DOF Tracking

• WaveNet: A Generative Model for Raw Audio

• The Microsoft 2016 Conversational Speech Recognition System

• Self-Normalizing Neural Networks

• Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours

• Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection

• 3D Simulated Robot Manipulation Using Deep Reinforcement Learning

• Deep-learning in Mobile Robotics - from Perception to Control Systems: A Survey on Why and Why not

• 3D Simulation for Robot Arm Control with Deep Q-Learning

• End-to-End Training of Deep Visuomotor Policies

• Leveraging Deep Reinforcement Learning for Reaching Robotic Tasks

• 100-epoch ImageNet Training with AlexNet in 24 Minutes

• Imagenet classification with deep convolutional neural networks

• Deep learning for detecting robotic grasps

• Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration

• Vision-based Robotic Arm Imitation by Human Gesture

• Supervision via Competition: Robot Adversaries for Learning Tasks

• Deep Visual Foresight for Planning Robot Motion

• Dermatologist-level classification of skin cancer with deep neural networks

• Brain tumor segmentation with deep neural networks

• SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

• Understanding image representations by measuring their equivariance and equivalence

• Understanding Deep Image Representations by Inverting Them

• YOLO9000: Better, Faster, Stronger

• Maxout Networks

• Going deeper with convolutions

• Training Very Deep Networks

• Batch normalization: Accelerating deep network training by reducing internal covariate shift

• Adam: A Method For Stochastic Optimization

• Dropout: A simple way to prevent neural networks from overfitting

• Delving deep into rectifiers: Surpassing human-level performance on imagenet classification

• Improving neural networks by preventing co-adaptation of feature detectors

• Fully Convolutional Networks for Semantic Segmentation

• PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization

• Systematic Testing of Convolutional Neural Networks for Autonomous Driving

• Deep Visual-Semantic Alignments for Generating Image Descriptions

• Audio Super Resolution using Neural Networks

• Very Deep Convolutional Networks for Large-scale Image Recognition

• Clinical Intervention Prediction and Understanding with Deep Neural Networks

• Toward Geometric Deep SLAM

• Robust Physical-World Attacks on Machine Learning Models

• Speeding up Semantic Segmentation for Autonomous Driving

• Connecting Images and Natural Language (Andrej Karpathy's Dissertation)

• Neocognitron: A Self-organizing Neural Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position

• Gradient-Based Learning Applied to Document Recognition

• Improving Neural Networks by Preventing Co-adaptation of Feature Detectors

• Visualizing and Understanding Convolutional Networks

• End to End Learning for Self-Driving Cars

• U-Net: Convolutional Networks for Biomedical Image Segmentation

• Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

• Explaining and Harnessing Adversarial Examples

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

• Why Does Deep and Cheap Learning Work So Well?

• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

• Modeling Smooth Backgrounds & Generic Localized Signals with Gaussian Processes (Kyle)

• Adversarial Variational Optimization of Non-Differentiable Simulators (Kyle)

Online Learning Resources

• Automated Machine Learning Hyperparameter Tuning in Python

• Rules of Machine Learning: Best Practices for ML Engineering

• Fast Near-Duplicate Image Search using Locality Sensitive Hashing

• Loc2Vec: Learning location embeddings with triplet-loss networks

• Using Word2Vec for Better Embeddings of Categorical Features

• Advances in Semantic Textual Similarity

• Privacy and machine learning: two unexpected allies?

• Information Theory of Neural Networks

• Stochastic Weight Averaging — a New Way to Get State of the Art Results in Deep Learning

• node2vec: Embeddings for Graph Data

• The fall of RNN / LSTM

• wav2letter: A Facebook AI Research(FAIR) Automatic Speech Recognition Toolkit

• Using Evolutionary AutoML to Discover Neural Network Architectures

• How to use Dataset in TensorFlow

• Using Tensorflow Object Detection to do Pixel Wise Classification

• Character-Level Language Model

• Understanding GANs through a statistical divergence perspective

• Deep Learning Book Series

• Understanding and optimizing GANs (Going back to first principles)

• Neural Artistic Style Transfer: A Comprehensive Look

• The Building Blocks of Interpretability

• Understanding Learning Rates and How It Improves Performance in Deep Learning

• Only Numpy: Implementing Highway Network, OOP approach with Mini Batch with Interactive Code

• Only Numpy: NIPS 2017 - Implementing Dilated Recurrent Neural Networks with Interactive Code

• Inverse Reinforcement Learning Pt. I

• Deep Learning in the Physical Sciences (Kyle)

• A Visual Guide to Evolution Strategies

• Terrence Parr and Jeremy Howard's math primer

• Annotating Large Datasets with the TensorFlow Object Detection API

• Deep Learning Is Not Good Enough, We Need Bayesian Deep Learning for Safe AI

• The Matrix Calculus You Need For Deep Learning

• Fast AI

• A visual introduction to machine learning

• SBNet: Leveraging Activation Block Sparsity for Speeding up Convolutional Neural Networks

• Only Numpy: Implementing GAN (General Adversarial Networks) and Adam Optimizer using Numpy with Interactive Code

• How to build your own AlphaZero AI using Python and Keras

• How Neural Networks Are Trained

• Inside the black box

• Inside the black box 2

• Geometric Deep Learning

• How To Unit Test Machine Learning Code

• Neuroevolution

• A set of Deep Reinforcement Learning Agents implemented in Tensorflow

• Deep Learning Adversarial Examples – Clarifying Misconceptions

• Understanding Autoencoders using Tensorflow

• Deep RL Bootcamp

• How to Define an Encoder-Decoder Sequence-to-Sequence Model for Neural Machine Translation in Keras

• Feature Visualization - How neural networks build up their understanding of images

• How to Develop a Character-Based Neural Language Model in Keras

• How-To: Multi-GPU training with Keras, Python, and deep learning

• Best Practices for Document Classification with Deep Learning

• GANs are Broken in More than One Way: The Numerics of GANs

• 37 Reasons why your Neural Network is not working

• Understanding LSTM Networks

• Michael Nielsen's Neural Networks and Deep Learning

• Leonardo Araujo dos Santos' Artificial Intelligence and Deep Learning GitBook

• CS231n Convolutional Neural Networks for Visual Recognition

• Deep Learning without Backpropagation (synthetic gradients)

• A quick complete tutorial to save and restore Tensorflow models

News

• The Wild Week in AI

• Ferenc Huszár's inFERENCe

• AAAI's AITopics Feed

Interesting Online Projects and Tools

• Neural BeatBox

• GuiTeNet

• The Mathematics of 2048: Optimal Play with Markov Decision Processes

• Embed, encode, attend, predict: The new deep learning formula for state-of-the-art NLP models

• Army develops face recognition technology that works in the dark

• Text Classification with TensorFlow Estimators

• MUNIT: Multimodal UNsupervised Image-to-image Translation

• wav2letter

• Generative Adversarial Networks for Extreme Learned Image Compression

• Splash of Color: Instance Segmentation with Mask R-CNN and TensorFlow

• Machine Learning is Fun Part 6: How to do Speech Recognition with Deep Learning

• Engineering Extreme Event Forecasting at Uber with Recurrent Neural Networks

• “Cracking” Morse code with RNNs

• Releasing “Supervisely Person” dataset for teaching machines to segment humans

• Only Numpy: Implementing Simple ResNet (Deep Networks with Stochastic Depth) for MNIST Classification with Interactive Code

• Only Numpy: Implementing Mini VGG (VGG 7) and SoftMax Layer with Interactive Code

• A Visual Guide to Evolution Strategies

• An overview of word embeddings and their connection to distributional semantic models

• Using OpenAI Gym with ROS

• Countering Adversarial Images Using Input Transformations

• tf-faster-rcnn

• Thinc

• Explosion.ai

• Deep Time-to-Failure

• Implementing GAN

• Detectron

• NVIDIA Researchers Showcase Major Advances in Deep Learning at NIPS

• Bayesian Generative Adversarial Networks in Tensorflow

• A neural network that solves polynomials

• GAN Playground - Explore Generative Adversarial Nets in your Browser

• Deep RL Bootcamp

• Demystifying Deep Reinforcement Learning

• Freeze Tensorflow models and serve on web

• A Tensorflow implementation of CapsNet(Capsules Net) in Hinton's paper Dynamic Routing Between Capsules

• GAN Playground - Explore Generative Adversarial Nets in your Browser

• Mask R-CNN for Object Detection and Segmentation

• Word2vec Tutorial

• Python gensim Word2Vec tutorial with TensorFlow and Keras

• A Word2Vec Keras tutorial

• Colorizing B&W Photos with Neural Networks

• Lyrebird

• Background removal with deep learning

• Teaching a car to avoid obstacles using Reinforcement Learning

• Audio Super Resolution Using Neural Networks

• Floyd

• Floyd All-in-one Docker Image

• Deep Learning Gallery

• DCGAN-tensorflow

• Image-to-image Demo

• Creating Photorealistic Images with Neural Networks and a Gameboy Camera

• Self-driving car in a simulator with A Tiny Neural Network

• Alex Champandard's Neural Doodle

• Alex Champandard's Neural Enhance

• Will Roscoe's Lane Following Autopilot with Keras & Tensorflow

• Julien Despois' Latent Space Visualization

• Alexia J-M's MEOW Generator (GAN applied to cat faces)

Data Sets

• Open Images Dataset V4

• ADEK20K

• Udacity's annotated driving dataset

• Stanford Car Data Set

• Comprehensive Car Data Set

• Playing for Data: Ground Truth from Computer Games

Support For Ideas

• AI Grant

• NVIDIA Inception Program

Online Programs of Study

• Some Thoughts on Mid-Career Switching Into Data Science

• Udacity

• Andrew Ng's deeplearning.ai

• Data School