Neural Networks and Deep Learning, free online book (draft)

By Gregory Piatetsky, @kdnuggets, Sep 20, 2014.

Here is a Machine Learning gem I found on the web:

a free online book on Neural Networks and Deep Learning , written by Michael Nielsen, a scientist, writer, and programmer.

The book covers:

• Neural networks, a biologically-inspired approach to machine learning
• Deep learning, a powerful (and very hot) set of techniques for learning in neural networks

 
Neural networks and deep learning currently provide the best solutions to many problems in image recognition, speech recognition, and natural language processing. This book teaches the core concepts behind neural networks and deep learning.

The book is written in a nice, visual, explanatory style and provides good examples while not shying away from math. Currently, the book is a draft, and has

• Chapter 1: how neural networks can learn to recognize handwriting
• Chapter 2: backpropagation, the most important algorithm used to learn in neural networks.
• Chapter 3: many techniques which can be used to improve the performance of backpropagation.
• Chapter 4: why neural networks can compute any function.

 
Planned chapters include

• Why deep neural networks are hard to train
• Deep learning
• The future of neural nets

 


Related:

• CuDNN - A new library for Deep Learning
• Deep Learning - important resources for learning and understanding
• Interview: Pedro Domingos: the Master Algorithm, new type of Deep Learning, great advice for young researchers
• Does Deep Learning Have Deep Flaws?