https://github.com/fxsjy/gonn

GoNN is an implementation of Neural Network in Go Language, which includes BPNN, RBF, PCN
https://github.com/fxsjy/gonn

Last synced: 18 days ago
JSON representation

GoNN is an implementation of Neural Network in Go Language, which includes BPNN, RBF, PCN

• Host: GitHub
• URL: https://github.com/fxsjy/gonn
• Owner: fxsjy
• Created: 2012-10-21T15:39:22.000Z (about 12 years ago)
• Default Branch: master
• Last Pushed: 2016-01-29T02:39:51.000Z (almost 9 years ago)
• Last Synced: 2024-11-16T20:43:59.133Z (26 days ago)
• Language: Go
• Homepage:
• Size: 11.4 MB
• Stars: 361
• Watchers: 35
• Forks: 53
• Open Issues: 4
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-golang-ai - gonn

README

        
GoNN [![GoDoc](https://godoc.org/github.com/fxsjy/gonn/gonn?status.svg)](https://godoc.org/github.com/fxsjy/gonn/gonn)

========

Neural Network in GoLang

Feature

=======

* BackPropagation Network / RBF Network / Perceptron Network

* Parallel BackPropagation Network (each neural has its own go-routine)

Benchmark

=======

* Dataset: MNIST Acurrency Rate : 98.2% (800 hidden nodes)

* Actually, you can get 96.9% using 100 hidden nodes in just three minutes of training

TODO

=======

* currently, the parallel version is much slower than the tranditional one, maybe caused by the cost of context switch of threads