Project Resource

Introduction

1. "Deep learning",  Yann LeCun, Yoshua Bengio & Geoffrey Hinton, Nature, Vol. 521, pp. 436-444, May 28, 2015.

Libraries

1. Theano is an open source project primarily developed by a machine learning group at the Université de Montréal. Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It has been powering large-scale computationally intensive scientific investigations since 2007.
2. Caffe is developed by the Berkeley Vision and Learning Center (BVLC) and by community contributors. It has been the most popular library for convolutional neural networks. It is a deep learning framework made with expression, speed, and modularity in mind. It is developed in C++, and has Python and MATLAB wrappers.
3. TensorFlow is developed by Google. TensorFlow is an open source software library for numerical computation using data flow graphs. TensorFlow runs on CPUs or GPUs, and on desktop, server, or mobile computing platforms. TensorFlow comes with a Python interface and a  C++ interface to build and execute your computational graphs.

Tools

1. ConvNetJS - ConvNetJS is a Javascript library for training Deep Learning models entirely in your browser. No software requirements, no compilers, no installations, and no GPUs.
2. Ersatz - Ersatz is a deep learning platform in the cloud for software engineers to develop their applications quickly. It offers data wrangling, deep learning, and an API.

Course

1. 
   
2. 
   
3. 
   

Paper

1. 
   
2. 
   
3. 
   

Theses/Dissertations

1.  
2.  
3.  

Perceptron (SLP & MLP)

1.  
2. 
   

Convolutional Neural Network (CNN)

1.  
2.  
3.  

Applications

1.  
2.  
3.