This is more or less just a random collection of links I've come across while researching Deep Learning, I hope they are as useful to you as to me.
Neural Networks, Manifolds, and Topology is a great post on how to visualize deep neural networks and get an intuition for them. Reading it was the first time I truly appreciated how the successive layers of NNs just transform the topology of the input data, until finally it becomes linearly separable.
So You Wanna Try Deep Learning? has a good collection of papers, articles and tips to get started with Deep Learning. In fact, some of the links in this article I first encountered there.
A Gentle Introduction to Backpropagation provides an unusual (but maybe easier to understand) look at back propagation, the essential algorithm for updating weights when training neural networks.
torch7 is a great framework to run machine learning algorithms, including everything you need to do deep learning on GPUs.
ImageNet Classification with Deep Convolutional Neural Networks is a very interesting landmark paper on the use of Deep Learning in Computer Vision.
Visualizing and Understanding Convolutional Networks helps immensely to understand how a convulutional network represents its features and how it generalizes in successive layers.
Stochastic Gradient Descent Tricks expands on stochastic gradient descent, the generalization of back propagation.
Tags: programming, ai