Deep Learning in Neural Networks: An Overview
by Juergen Schmidhuber
Publisher: arXiv 2014
Number of pages: 88
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarises relevant work, much of it from the previous millennium.
Home page url
Download or read it online for free here:
by Yoshua Bengio, Ian Goodfellow, Aaron Courville - MIT Press
This book can be useful for the university students learning about machine learning and the practitioners of machine learning, artificial intelligence, data-mining and data science aiming to better understand and take advantage of deep learning.
by Thomas Epelbaum - arXiv.org
This note presents in a technical though hopefully pedagogical way the three most common forms of neural network architectures: Feedforward, Convolutional and Recurrent. For each network, their fundamental building blocks are detailed.
by LISA lab - University of Montreal
This book will introduce you to some of the most important deep learning algorithms and show you how to run them using Theano. Theano is a python library that makes writing deep learning models easy, and gives the option of training them on a GPU.
by Terence Parr, Jeremy Howard - arXiv.org
This paper is an attempt to explain all the matrix calculus you need in order to understand the training of deep neural networks. We assume no knowledge beyond what you learned in calculus 1, and provide links to help you refresh the necessary math.