Multi-Layer Perceptron Neural Network

This is a sqlite backed version of my previous MLP.

This version also provides training validation to prevent the MLP from overfitting.

This is first release and because of that it’s a bit slow, I’ll probably try out using Memcached or something else as its data store.

Install

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

How To Use

require 'rubygems'
require 'db_mlp'

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

training = [[[0,0], [0]], [[0,1], [1]], [[1,0], [1]], [[1,1], [0]]]
testing = [[[0,0], [0]], [[0,1], [1]], [[1,0], [1]], [[1,1], [0]]]
validation = [[[0,0], [0]], [[0,1], [1]], [[1,0], [1]], [[1,1], [0]]]

a.train(training, testing, validation, number_of_training_iterations)

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}"

Benchmarks

The above example produces these times

                user     system      total        real
DBMLP    9.100000   0.040000   9.140000 (  9.170872)

Copyright

Copyright © 2009 Red Davis. See LICENSE for details.