Skip to content

This java library is used for generating, training, and using artificial neural networks with linear algebra. Uses feed forward nets, with backpropagation learning algorithm.

wateryan/NeuralNetwork

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

35 Commits
 
 
 
 
 
 

Repository files navigation

NeuralNetwork

This is a Java library for creating artificial neural networks. It can:

  • Create Neural Networks
  • Train Neural Networks using backpropagation, optimized with linear algebra
  • Run Neural Networks
  • Debug with testing functions

The digitInput.txt is a matrix with 5000 20px by 20px images. The digitOutput.txt gives the correct digit for each of the 5000 images. (Each row of the matrix is one image, so digit Input is a 5000x400 matrix and digitOutput is a 5000x10 matrix).

Note: this library requires the jblas linear algebra library. (jblas.org)

Note: this library has only been tested on Linux (Ubuntu 12.04 x64)

About

This java library is used for generating, training, and using artificial neural networks with linear algebra. Uses feed forward nets, with backpropagation learning algorithm.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Java 100.0%