I am exploring some frontiers in machine learning techniques for gaze / visual behavior classification. I am really interested in how Deep Learning yields sophisticated results for complex tasks. Listed below are some references I used to read :
- What’s the difference between AI, Machine Learning, and Deep Learning ?
- What is deep learning : A Pete Warden article in O’Reilly
- NVidia Deep Learning page
- MIT Press Deep Learning Book
- Deep Learning Dot Net Reading List
- Quora’s : What’s Deep Learning ?
- The Extraordinary Link Between Deep Neural Networks and The Nature of Universe
Useful links from academia :
Some readings in progress :
- Kevin P Murphy’s : Machine Learning – A Probabilistic Perspective
- Rogers and Girolami’s : A First Course in Machine Learning 1st Edition
List of deep learning resources from across the web
See the original post here
Books
- DeepLearningBook.org by Ian Goodfellow, Yoshua Bengio and Aaron Courville
- NeuralNetworksandDeepLearning.com by Michael Nielsen
Courses
- Neural Networks for Machine Learning (2017) by Geoffrey Hinton, University of Toronto
- CS231n Convolutional Neural Networks for Visual Recognition by Andrej Karpathy, Stanford University
- Natural Language Processing with Deep Learning by Christopher Manning and Richard Socher, Stanford University
- Deep Natural Language Processing (2017) by Phil Blunsom, Oxford University and Google DeepMind
- Deep learning (2015) by Nando de Freitas, Oxford University
- Deep Learning for Self-Driving Cars (2017) by Lex Fridman, Massachusetts Institute of Technology
- Deep Learning by Google (on Udacity)
Blogs
Newsletters
- Weekly newsletter on Deep Learning & AI
- The Wild Week in AI
- Deep Learning Weekly
- Transmission – Self-Driving Car & Deep Learning Newsletter
Research paper by subfield
- Reading List « Deep Learning
- The most cited deep learning papers
- Deep Learning papers reading roadmap
- Amund Tveit’s Blog
Learn deep learning, from novice to advanced, self-paced
See the original post here
Tutorials have been chosen to maximize learning curve, i.e. learn the most in the shortest amount of time. Tutorials cover topics from basic deep learning all the way to research done within the last 1 year! They cover significantly more material than a typical deep learning course and take lesser time.
Expected time to completion: 4-6 weeks (20-30 sessions)
Pre-requisites: Calculus (specifically, differentiation)
We’ll cover the following topics:
- Machine Learning basics (what it is, gradient descend)
- Deep Learning basics (what it is, neural networks, computational graphs, back-propagation)
- Convolutional Neural Networks (mostly applied to computer vision)
- Recurrent Neural Networks (mostly applied to natural language processing)
- Generative Adversarial Networks and Variational Auto-Encoders (mostly applied to image generation)
- Deep Reinforcement Learning
Pro-tip: If you want to skip sections or tutorials, mark them as completed.
A Visual Introduction to Machine Learning
A Machine Learning Introductory Tutorial with Examples
Deep Learning Tutorial: Perceptrons to Machine Learning Algorithms
Andrej Karpathy: Yes you should understand backprop
Calculus on Computational Graphs: Backpropagation — colah’s blog
A Beginner’s Guide To Understanding Convolutional Neural Networks – Adit Deshpande
A Beginner’s Guide To Understanding Convolutional Neural Networks Part 2 – Adit Deshpande
Conv Nets: A Modular Perspective
Understanding Convolutions — colah’s blog
Visualizing Features from a Convolutional Neural Network
Understanding CNNs Part 3: The 9 Deep Learning Papers You Need To Know About – Adit Deshpande
Neural Network Architectures in Computer Vision
Deconvolution and Checkerboard Artifacts
Breaking Linear Classifiers on ImageNet
Understanding LSTM Networks — colah’s blog
The Unreasonable Effectiveness of Recurrent Neural Networks – Andrej Karpathy
Deep Learning, NLP, and Representations
Deep Learning Research Review: Natural Language Processing – Adit Deshpande
Attention and Augmented Recurrent Neural Networks
Neural Networks, Manifolds, and Topology — colah’s blog
Deep Learning Research Review: Generative Adversarial Nets – Adit Deshpande
Generative Adversial Networks Explained
Variational Autoencoders Explained
What is DRAW (Deep Recurrent Attentive Writer)?
Deep Learning Research Review: Reinforcement Learning
Deep Reinforcement Learning: Pong from Pixels
Paper Summary: Human-Level Control Through Deep Reinforcement Learning
Four Experiments in Handwriting with a Neural Network
Neural Networks, Types, and Functional Programming — colah’s blog
