Multi-Layer Perceptron Neural Network¶ ↑

I built this to not only learn about the MLP but to also make a very simple, well laid out MLP so other can easily see what’s happening.

I also suggest checking out bit.ly/XEWOc for a great tutorial.

gem sources -a http://gems.github.com
sudo gem install reddavis-mlp

require 'rubygems'
require 'mlp'

a = MLP.new(:hidden_layers => [2], :output_nodes => 1, :inputs => 2)

3001.times do |i|
  a.train([0,0], [0])
  a.train([0,1], [1])
  a.train([1,0], [1])
  error = a.train([1,1], [0])
  puts "Error after iteration #{i}:\t#{error}" if i%200 == 0
end

puts "Test data"
puts "[0,0] = > #{a.feed_forward([0,0]).inspect}"
puts "[0,1] = > #{a.feed_forward([0,1]).inspect}"
puts "[1,0] = > #{a.feed_forward([1,0]).inspect}"
puts "[1,1] = > #{a.feed_forward([1,1]).inspect}"

The above example produces these times

         user     system      total        real
MLP    0.820000   0.000000   0.820000 (  0.837693)
Ai4R   1.180000   0.010000   1.190000 (  1.232388)

• David Richards - For his code reviews and all round helpfulness. - github.com/davidrichards

Copyright © 2009 Red Davis. See LICENSE for details.