Skip to content

WISARD pattern recognition implemented using webgl shader language.

Notifications You must be signed in to change notification settings

malcolmbinstead/wisard

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Wisard

WISARD is an early example of a hardware neural network pattern recognition machine (1981) (https://en.wikipedia.org/wiki/RAMnets#RAM-discriminators_and_WiSARD).

WISARD was designed and built by Bruce Wilkie at Brunel University as part of his Phd project with the backing of Professor Igor Aleksander and Dr John Stonham.

WISARD was a hardware machine that used a parallel architecture to run at video frame rates.

WISARD is on display at the Science Museum in the Winton Gallery (https://www.sciencemuseum.org.uk/learning/mathematics-winton-gallery-school-info).

This project is a software implementation of WISARD that performs the processing steps within your browser.

This implementation is written in Typescript as an Angular 7 service.

This implementation uses WebGL2 and the Shading Language to accelerate the processing pipeline.

This demonstration uses a SPA (https://en.wikipedia.org/wiki/Single-page_application) top-level application to walk you through WISARD's processing steps.

A runnable demo can be found at: https://malcolmbinstead.github.io/wisard/

And the source code can be found at: https://github.com/malcolmbinstead/wisard

Please note that this demo requires that you are using a browser and display card that supports webgl2.

About

WISARD pattern recognition implemented using webgl shader language.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages