Skip to content

Artificial neural network, learned by error backpropagation algorithm, written in Javacript with asynchronous computation

Notifications You must be signed in to change notification settings

johnygomez/Visual-Backprop-JS

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Visual Backprop JS

Neural network simulator, written purely in Javascript.

Try it at Example

In src/ folder, you can find source files for NN back-end (Backprop). Source files were built with Browserify.

In js/ folder, you can find source files for client side.

  • netAsync.js is definition of web worker performing background computation
  • network.js is main file for client application, controlling UI events and network tasks (drawing error, result, learning...)
  • netPlumb.js Defines connectable network UI in JsPlumb

Visual part of application was developed using JQuery and Bootstrap for visual elements. Connectable network was developed using JsPlumb. Graphs are drawn with ChartJS library.

#Thanks for contributing

About

Artificial neural network, learned by error backpropagation algorithm, written in Javacript with asynchronous computation

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published