Bugfinder Hall of Fame

Neural Networks and Deep Learning

What this book is about

On the exercises and problems

Using neural nets to recognize handwritten digits

How the backpropagation algorithm works

Improving the way neural networks learn

A visual proof that neural nets can compute any function

Why are deep neural networks hard to train?

Deep learning

Appendix: Is there a simple algorithm for intelligence?


Frequently Asked Questions



Thankyou to the following people for their help in finding and eliminating bugs and other errors in the book:

Kartik Agaram, Martin Aulbach, Joseph Barrow, Maxim Baz, Ingo Blechschmidt, Charles Brauer, Greg Brockman, Cristi Burcă, Josue Ortega Caro, Gildas Chabot, Jen Dodd, Philipp Düren, Chris Ferrie, Tim Gowers, Timo Hannay, Vojtěch Havlíček, Nikola Henezi, Jay Huie, Michael Lennon, Hassan Masum, John McNally, pyos, Juergen Schmidhuber, Sharad Sundararajan, D. Sivakumar, Jeremy Vonderfecht, and Nico Weber.