DEEP BLUEBERRY BOOK
🐳 ☕️ 🧧
This is a tiny and very focused collection of links about deep learning. If you've always wanted to learn deep learning stuff but don't know where to start, you might have stumbled upon the right place!
- Deep Learning Foundations
- Deep Computer Vision
- Deep Sequence Models
- Deep Generative Models
- Deep Reinforcement Learning
- Deeper: What's next?
This self-learning plan is split into five modules and designed to be completed in five weekends. Per module, you might want to take about four hours to digest the theory plus an additional six or more hours to experiment with available code.
Prerequisites
- Familiarity with basic multivariate calculus, linear algebra, probability, statistics
- Coding experience with Python or any other programming language
- (Recommended) S Keshav: How to Read a Paper
🐳 🐳 🐳
33Mudy961bUk9zz35p68g9fE3uuHLRduRp
Deep Learning Foundations
🐳 ☕️ 🧧
- Learn the principles behind deep learning and artificial neural networks
- Implement simple feedforward neural networks with Tensorflow Keras and PyTorch
Videos + Readings
65 min2017-Oct3Blue1Brown: Neural Networks Playlist19 minBut what is a Neural Network?21 minGradient descent, how neural networks learn14 minWhat is backpropagation really doing?11 minBackpropagation calculus
24 min2017-MarBrandon Rohrer: How Deep Neural Networks Work45 min2019-JanAlexander Amini: Introduction to Deep Learning2015-JunMichael Nielsen: A visual proof that NNs can compute any function2017-MayJonathan Uesato: What is an ablation study? (Quora)
Coding Exercises
- Andrej Karpathy | Denny Britz - Build Neural Networks from Scratch
- Soumith Chintala: PyTorch 60 Minute Blitz
- Tensorflow Keras | PyTorch Tutorials | FChollet Tutorials
🐳 🐳 🐳
33Mudy961bUk9zz35p68g9fE3uuHLRduRp
Deep Computer Vision
🐳 ☕️ 🧧
- Learn what a convolutional neural network is and the mathematics behind recognizing images
- Be familiarized with widely-used techniques like transfer learning, feature preprocessing, data augmentation, and layer visualization
Videos + Readings
18 min2015-MarFei Fei Li: How we teach computers to understand pictures16 min2017-MayCaryk Huang: Teaching my computer to give me friends27 min2016-AugBrandon Rohrer: How CNNs work2018-JunIrhum Shafkat: Intuitively understanding convolutions for deep learning33 min2017-MarLuis Serrano: A friendly introduction to CNNs and image recognition- Andrej Karpathy: Visualizing what CovNets learn
- Adam Harley: Interactive Visualization of CNN
Coding Exercises
2017-JanAlex Staravoitau: Traffic Sign Classification- Sasank Chilamkurthy: Classifying ants and bees (Transfer Learning)
2016-JanFrancois Chollet: How convolutional neural networks see the world- Alexis Jacq: Neural Transfer Using PyTorch
🐳 🐳 🐳
33Mudy961bUk9zz35p68g9fE3uuHLRduRp
Deep Sequence Models
🐳 ☕️ 🧧
- Learn how RNNs (LSTMs, GRUs) work and why they are used to process sequences
Videos + Readings
40 min2015-SepAndrej Karpathy: Visualizing and Understanding Recurrent Networks2015-AugChristopher Olah: Understanding LSTM Networks24 min2018-SepMichael Nguyen: An illustrated Guide to RNN and LSTM27 min2017-JunBrandon Rohrer: RNN and LSTM2019-JanAva Soleimany: Deep Sequence Modeling
🐳 🐳 🐳
33Mudy961bUk9zz35p68g9fE3uuHLRduRp
Deep Generative Models
🐳 ☕️ 🧧
- Learn how Generative Adversarial Networks and Variational Autoencoders can produce realistic, never-before-seen data
Videos + Readings
VARIATIONAL AUTOENCODERS
2018-FebIrhum Shafkat: Intuitively Understanding Variational Autoencoders2018-MarJeremy Jordan: Variational Autoencoders2017-DecKeita Kurita: An Intuitive Explanation of Variational Autoencoders2017-MayWill Kurt: Kullback-Leibler Divergence Explained
GENERATIVE ADVERSARIAL NETWORKS
2016-JunKevin Frans: Generative Adversarial Networks Explained22 min2017-OctRob Miles: Generative Adversarial Networks (GANs)2019-JanMinsuk Kahng et al: Play with Generative Adversarial Network in Your Browser2019-JanMadhu Sanjeevi: Generative Adversarial Networks with Math
Coding Exercises
21 min2018-JulJohn Fisher: Autoencoder Tutorial in Keras- MIT Bootcamp: Intro to Deep Learning Debiasing Faces
17 min2018-JanDominic Mon: Make a Face Adversarial Network in 15 minutes- Erik Linder-noren: PyTorch-GAN
🐳 🐳 🐳
33Mudy961bUk9zz35p68g9fE3uuHLRduRp
Deep Reinforcement Learning
🐳 ☕️ 🧧
- Understand the core ideas and terminologies used in the field
- Understand a few reinforcement learning algorithms
- Apply these algorithms to videogame-like environments such as OpenAIGym and MuJoCo
Readings + Coding Exercises
2017-NovJosh Greaves: Understanding Reinforcement Learning- Jaromír Janisch: Let's Make DQN and A3C series
2016-SepLet's Make DQN Theory2017-FebLet's Make A3C Theory
2018-MarThomas Simonini: Deep Reinforcement Learning (free course)
Advanced Material
- Dulat Yerzat: RL Adventure on DQN and Policy Gradients
2018-NovJosh Achiam: OpenAI Spinning Up (free course)
🐳 🐳 🐳
33Mudy961bUk9zz35p68g9fE3uuHLRduRp
Deeper: What's next?
🐳 ☕️ 🧧
If you've finished all five modules, congratulations! 🎉🎉 You are now familiar with some of the hottest topics in deep learning today. You might want to continue your deep learning journey with the links listed below. 🚀 are must-clicks!
2018-MarTess Ferrandez: Notes from Andrew Ng's courses2016-JanSebastian Ruder: Gradient Descent Optimization Algorithms2016-SepFjodor Van Veen: The Neural Network Zoo- 🚀 Distill.pub: A modern medium presenting research
18 min2015-FebIan Goodfellow: Adversarial Examples- 🚀
37 min2019-JanAva Soleimany: Limitations and New Frontiers - 💰💰 Brandon Rohrer: Neural Network Visualization
- 🚀 Fast.AI: Practical and Cutting-Edge Deep-learning for Coders (free course)
2018-NovLilian Weng: Meta-Learning: Learning to Learn Fast52 min2017-DecPieter Abbeel: Deep Learning for Robotics43 min2018-JanDavid Silver: Mastering games without Human Knowledge- Papers with Code | Zaur Fataliyev: PWC
🐳 🐳 🐳
33Mudy961bUk9zz35p68g9fE3uuHLRduRp