• Deep learning core concepts.
• Deep learning training.
• Understanding LSTM networks
• The Unreasonable Effectiveness of Recurrent Neural Networks shows a bunch of real life examples
• Deep Learning, NLP, and Representations for an overview on word embeddings and RNNs for NLP
• Understanding LSTM Networks is about LSTMs work specifically, but also informative about RNNs in general
• Calculus on Computational Graphs

More examples:

• apachecn/MachineLearning
• Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow
• lawlite19/DeepLearning_Python
• A collection of tutorials and examples for solving and understanding machine learning and pattern classification tasks
• Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech
• Content for Udacity's Machine Learning curriculum
• This is the lab repository of my honours degree project on machine learning
• A curated list of awesome Machine Learning frameworks, libraries and software
• Bare bones Python implementations of some of the fundamental Machine Learning models and algorithms
• The "Python Machine Learning" book code repository and info resource

PyTorch 0.4+ is recommended.

• Offical PyTorch tutorials for more tutorials (some of these tutorials are included there)
• PyTorch Basics

• Convolutional Neural Network
• Deep Residual Network
• Recurrent Neural Network
• Bidirectional Recurrent Neural Network
• Language Model (RNN-LM)

• Image Captioning (CNN-RNN)
• Deep Convolutional GAN (DCGAN)
• Variational Auto-Encoder
• Neural Style Transfer
• Generative Adversarial Networks
• Variational Auto-Encoder
• Neural Style Transfer
• Image Captioning (CNN-RNN)

• TensorBoard in PyTorch

• spro/practical-pytorch
• jcjohnson's PyTorch examples for a more in depth overview (including custom modules and autograd functions)
• chenyuntc/pytorch-book

TensorFlow v2.0 is recommended.

• Hello World (notebook). Very simple example to learn how to print "hello world" using TensorFlow 2.0.
• Basic Operations (notebook). A simple example that cover TensorFlow 2.0 basic operations.

• Linear Regression (notebook). Implement a Linear Regression with TensorFlow 2.0.
• Logistic Regression (notebook). Implement a Logistic Regression with TensorFlow 2.0.
• Simple Neural Network (notebook). Implement a Simple Neural Network with TensorFlow 2.0.
• Create your own layer (notebook). Create your own layer with TensorFlow 2.0.

• Simple Neural Network (notebook). Use TensorFlow 2.0 'layers' and 'model' API to build a simple neural network to classify MNIST digits dataset.
• Simple Neural Network (low-level) (notebook). Raw implementation of a simple neural network to classify MNIST digits dataset.
• Convolutional Neural Network (notebook). Use TensorFlow 2.0 'layers' and 'model' API to build a convolutional neural network to classify MNIST digits dataset.
• Convolutional Neural Network (low-level) (notebook). Raw implementation of a convolutional neural network to classify MNIST digits dataset.

• Auto-Encoder (notebook). Build an auto-encoder to encode an image to a lower dimension and re-construct it.
• DCGAN (Deep Convolutional Generative Adversarial Networks) (notebook). Build a Deep Convolutional Generative Adversarial Network (DCGAN) to generate images from noise.

• Save and Restore a model (notebook). Save and Restore a model with TensorFlow 2.0.
• Build Custom Layers & Modules (notebook). Learn how to build your own layers / modules and integrate them into TensorFlow 2.0 Models.

Julia: Looks like Python, feels like Lisp, runs like Fortran

As ML models began to need the full power of a programming language,getting Python to scale to ML’s heavy computational demands is far harder than you might expect. Python’s semantics also make it fundamentally difficult to provide model-level parallelism or compile models for small devices.

More details:

• On Machine Learning and Programming Languages
• Why your next project should use Julia

• Tutorials and information on the Julia language for MIT numerical-computation courses
• An Introduction to Julia for Data Science and Scientific Computing
• Introducing Julia wikibook
• Learn Julia the hard way
• Hands-on Julia
• The-Julia-Express
• Julia by Example
• Learn Julia via Examples
• Programming in Julia (Quantitative Economics)

• Machine Learning, Neural Networks, NLP, Speech Recognition and Voice tools
• Julia implementation of the scikit-learn API
• Mocha.jl - Deep Learning framework for Julia
• Merlin.jl - Deep Learning for Julia
• Knet.jl - Koç University deep learning framework
• Julia package for text analysis
• MXNet Julia Package - flexible and efficient deep learning in Julia
• A Julia wrapper for TensorFlow
• Flux is the ML library that doesn't make you tensor
• A julia wrapper for Keras

• A Julia cheat sheet
• A Fast Track to Julia: A Quick and Dirty Overview (Cheatsheet)
• Curated decibans of Julia language
• Julia Observer - A website for browsing Julia packages