Coder Social home page Coder Social logo

antonvladyka / neuralnetworksanddeeplearning.com.pdf Goto Github PK

View Code? Open in Web Editor NEW
265.0 22.0 79.0 56.11 MB

LaTeX/PDF + Epub version of the online book (http://neuralnetworksanddeeplearning.com) ”Neural Networks and Deep Learning“ by Michael Nielsen (@mnielsen)

TeX 98.96% Python 1.04%
neural-network neural-networks deep-learning machine-learning latex

neuralnetworksanddeeplearning.com.pdf's Introduction

Neural Networks and Deep Learning

by Michael Nielsen

This is an attempt to convert online version of Michael Nielsen's book 'Neural Networks and Deep Learning' into LaTeX source.

Current status

  1. Chapter 1: done
  2. Chapter 2: done
  3. Chapter 3: done
  4. Chapter 4: includes a lot of interactive JS-based elements. In progress. By now, interactive elements are replaced with intuitive (I hope) graphs, but text is not fully adapted.
  5. Chapter 5: done
  6. Chapter 6: done

I observed some missed Python code in the online version of network3.py:

   print('The corresponding test accuracy is {0:.2
   test_accuracy))
   ...
   print("Best validation accuracy of {0:.2
      best_validation_accuracy, best_iteration))
   ...
   print("Corresponding test accuracy of {0:.2

So, these parts were replaced with the correct ones from the source code repo.

Can be compiled into any desired format, using XeLaTeX — with any desired font.

As a general design, I used my PhD thesis style: 17x24 cm paper, 9pt font, Charter/Mathdesign, own designed chapter titles, chapter labels etc.

Typography adjusted (- → –, "" → “ ”)

Bibliography — maybe to collect all cited research papers?

Update 07.10.2018

Equation numbering is updated to sequential as in the original online book. Please note that some numbers are missing (e.g. 40-41), since some equations in the online book are multiline with a label on every line. I use the same tags/numbers as in the book.

Epub 01.11.2019

Epub version added.

pandoc -s --mathml book.tex -o book.epub

converts source latex files into epub with formulas redneder by MathML. MathML works correctly in Calibre.

Please note: pandoc does not produce images from tikzpicture, therefore chapter 4 in epub is corrupted with missing images. It in much better to check Chapter 4 online anyway, since it contains interactive elements.

neuralnetworksanddeeplearning.com.pdf's People

Contributors

antonvladyka avatar daniel-mietchen avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

neuralnetworksanddeeplearning.com.pdf's Issues

Interactive from Chapter 4

Currently instead of interactive elements I use 2-3 plots with different parameters which can be changed.

EPUB output

Great job on the book! I was wondering, can you compile an EPUB for this book? This would make very ebook reader friendly. Since it's in latex, it shouldn't be that much of a problem.

Latex in epub version

Hi, thanks for your work, this is amazing !

A small feedback:

I have noticed the latex equations are not converted, that is they stay as plain latex language.
I've opened the epub using iBooks on a Mac if that helps.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.