Neuroph

Neuroph

Stable release	2.5RC1 / April 17, 2011 (2011-04-17)
Written in	Java
Platform	Java platform
Available in	English
Type	Neural network
License	Apache License
Website	neuroph.sourceforge.net

Neuroph is an object-oriented neural network framework written in Java. It can be used to create and train neural networks in Java programs. Neuroph provides Java class library as well as GUI tool easyNeurons for creating and training neural networks.

It is the open source project hosted at SourceForge, and the latest version 2.7 has been released under the Apache License. Previous versions were licensed under LGPL.

Features

Neuroph core classes correspond to basic neural network concepts like artificial neuron, neuron layer, neuron connections, weight, transfer function, input function, learning rule etc. Neuroph supports common neural network architectures such as Multilayer perceptron with Backpropagation, Kohonen and Hopfield networks. All these classes can be extended and customized to create custom neural networks and learning rules. Has built in support for image recognition.

See also

• Neural network
• SOM or Kohonen
• Retropropagation

External links

• Neuroph Homepage
• Online Demo
• Slashdot: Java Program Uses Neural Networks To Monitor Games
• DZone: Neuroph-Smart Java Apps with Neural Networks(Part 1)
• Dzone: Neuroph-Smart Java Apps with Neural Networks(Part 2)
• Image recognition with Neuroph example