Introduction to Deep learning Introductory series 2

Note: This page is a guided page, followed by 7 major tutorials and some high-level examples, step by step to explain deep learning.

The tutorials here will provide you with some of the most important deep learning algorithms, and will also tell you how to use Theano to run them. Theano is a Python class library that helps you write deep algorithm models easily and allows you to run these algorithms on the GPU

Before you learn these tutorials, you need to familiarize yourself with the Theano, here is the basic tutorial, after learning, then look at this stuff, there are some basic concepts and some test training set.


A purely supervised learning algorithm needs to be learned in the following order:
1, Logistic regression
2, Multilayer Perceptron
3, deep convolutional nets


Unsupervised learning and semi-supervised learning algorithms can be learned in any order (followed by tutorials and code)


1,auto encoders denoising autoencoders
2, stacked denoising auto-encoders simple steps to achieve unsupervised learning
3, limit the Boltzmann machine
4,DBN HTTP://DEEPLEARNING.NET/TUTORIAL/DBN.HTML#DBN




If you are building the MCRBM model, here is a new tutorial on energy models, HMC sampling (to be continued)


If you want to create the contractive auto-encoders, here is the source code (to be continued)


If you want to create recurrent neural networks with Word embeddings and context window here is the tutorial. adjourned


If you want to create energy-based recurrent neural Network (RNN-RBM): Here is the tutorial (to be continued)

Introduction to Deep learning Introductory series 2