Neural Networks and Deep Learning Book Project

A book that will teach you the core concepts of neural networks and deep learning
Pf6flnm1etz0bcqwi5vc
Michael Nielsen
Technology
Toronto, Ontario
Canada
1 Team Member

About the book

This book will teach you the core concepts of neural networks and deep learning.  These are powerful machine learning techniques which have achieved outstanding results for problems in image recognition, speech recognition, and natural language processing.  Neural networks and deep learning are now being adopted by many companies, including Google, Microsoft, and Facebook.

I'm writing this book to bridge the gap between popular accounts and the many technical papers on neural networks and deep learning. The book will make it easy and fun for people with programming and basic mathematical skills to come up to speed.

I love explaining complex technical subjects.  I've written two previous books.  The first book, "Quantum Computation and Quantum Information" (joint with Ike Chuang), is the standard text on quantum computing, and one of the ten most cited books in the history of physics. The second book, "Reinventing Discovery: The New Era of Networked Science", is a book for a general audience about networked science.  It was named one of the best books of 2011 by The Financial Times  and the Boston Globe.  

In addition to my books I've written many technical articles, including "Lisp as the Maxwell's equations of software", "How to crawl a quarter billion webpages in 40 hours", and "Why Bloom filters work the way they do", all of which made the top five posts on Hacker News.

You can see a draft of chapter 1 of the book at neuralnetworksanddeeplearning.com.

The book will be made freely available online, under a Creative Commons Attribution-Non-Commercial license.

As an independent writer and scientist, the reason I'm undertaking this Indiegogo campaign is to give me some partial support while I complete the book. 

Draft table of contents

  • Using neural nets to recognize handwritten digits: We get off to a flying start, creating a neural network that can solve a hard problem - recognizing handwritten digits.
  • Using backpropagation to speed up learning: We'll master the ins-and-outs of the backpropagation algorithm, which is the fundamental algorithm used to learn in neural nets, and the basis for deep learning.
  • Neural nets: the big picture:  How do artificial neural nets compare to biological brains? Is there a simple universal algorithm for thinking? How can we use neural nets to solve problems in speech recognition and natural language processing? Can we use neural nets to compute an arbitrary function?
  • Deep learning: What makes deep neural networks hard to train with conventional approaches?  How can we overcome those challenges? We'll see how deep neural nets can be pre-trained, and how they can learn high-level representations of knowledge from complex data.
  • Recent progress in image recognition: We'll dive into exciting recent work using deep learning to solve difficult problems in image recognition, including recognizing the images in ImageNet, and the Stanford-Google "cat neuron" paper.
  • The future of neural nets: Will neural nets help lead to artificial intelligence?  Can they be used to simulate a human brain?
Find This Campaign On
$9,502CAD
raised by 333 people in 22 days
190% funded
No time left
$5,000 CAD goal
Flexible Funding This campaign has ended and will receive all funds raised.
Campaign Closed
This campaign ended on December 16, 2013
Select a Perk
  • $5CAD
    Supporter

    You'll be listed as a supporter on the book web site (but you can, of course, opt out).

    17 claimed
    Estimated delivery: January 2014
  • $15CAD
    Early Access

    Early access to draft chapters of the book as they become available. You'll have access for at least six weeks (and sometimes more) before chapters go live online for a general audience. The first draft chapter will become available in February 2014; more will become available later in 2014.

    290 claimed
    Estimated delivery: February 2014
  • $200CAD
    Online Discussion

    One hour Skype discussion of neural nets, deep learning, or anything else you'd like to chat about (quantum computing, if that's your kick!) Plus all of the above rewards.

    8 out of 20 claimed
    Estimated delivery: January 2014
  • $500CAD
    Major Sponsor

    You'll receive major billing as a book patron on the book web site. Plus all of the above rewards.

    5 claimed
    Estimated delivery: January 2014
Do you think this campaign contains prohibited content? Let us know.
Other Campaigns You Might Like