Basic Neural Networks
The first link gives some background on auto encoders and the second link is to an online text extract providing an overview of several additional basic DNN architectures. The third link is to a set of online tutorials from Stanford. The fourth link is to a preprint of a deep learning textbook written by Yoshua Bengio, professor at the Department of Computer Science and Operations Research at Université de Montréal, and Ian Goodfellow. The fifth link is to Theano (a python library for GPU machines) code for deep learning. The sixth link is a tutorial video by Geoffrey Hinton, Yann LeCun, and Yoshua Bengio, and the seventh link is for the slides for the NIPS tutorial. A bunch of tools and tutorials follow.
Basic types of deep neural network architectures
Stanford Deep Learning Tutorial
http://www.deeplearningbook.org
http://deeplearning.net/tutorial/
Deep Learning in a Nutshell – what it is, how it works, why care?
The mostly complete chart of Neural Networks, explained
CNNs
Intuitively Understanding Convolutions for Deep Learning
How to Design a Convolutional Neural Network
RNNs
Recurrent Neural Networks and LSTM
Reinforcement Learning
Sutton, Barto — Reinforcement Learning: An Introduction
Learning Reinforcement Learning (with Code, Exercises and Solutions)
Deep Learning in a Nutshell: Reinforcement Learning
MIT Technology Review: 10 Breakthrough Technologies — Reinforcement Learning
Reinforcement learning tutorial with TensorFlow
Tools
How to build your own Neural Network from scratch in Python
Dopamine: Reinforcement Learning Research Framework built atop TensorFlow
TensorBoard: Visualizing Learning
TensorFlow Fold: Deep Learning With Dynamic Computation Graphs
TensorFlow Probability: Library for Probabilistic Reasoning and Statistical Analysis in TensorFlow
The Matrix Calculus You Need For Deep Learning
Where did the Least Square Come From?
Best Practices/Parameter Setting