Skip to content
A neural network in Julia
Branch: master
Clone or download
compressed Merge pull request #8 from tkelman/travisver
use version number instead of release in .travis.yml
Latest commit fc1de5b May 24, 2017
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
perf
src Fix deprecation and breakage Dec 15, 2015
test Neural.jl -> BackpropNeuralNet.jl Dec 12, 2014
.travis.yml
LICENSE.md Changed license to have correct package name Jan 18, 2016
README.md docs(README): update badge URLs Dec 24, 2015
REQUIRE chore(REQUIRE): add REQUIRE file Dec 30, 2015

README.md

Build Status Coverage Status BackpropNeuralNet BackpropNeuralNet

Install

Stable

Pkg.add("BackpropNeuralNet")

Source

Pkg.clone("https://github.com/compressed/BackpropNeuralNet.jl.git")

Usage

To initialize a network of 2 inputs, 1 hidden layer with 3 neurons, and 2 outputs:

using BackpropNeuralNet

net = init_network([2, 3, 2])

# To train the network use the form `train(network, input, output)`:
train(net, [0.15, 0.7],[0.1, 0.9])

# To evaluate an input use the form `net_eval(network, inputs)`
net_eval(net, [0.15, 0.7])

History

This is a Julia implementation of a neural network based on Sergio Fierens ruby version.

You can’t perform that action at this time.