Main Page

ANN - Artificial Neural Network for PHP 5.x

This project realizes a neural network topology called multilayer perceptron for PHP 5.x environments. The source code is based on a work by Eddy Young in 2002. Several improvements and changes on this implementation are done by Thomas Wien in 2007. You will find the PHP source in the section Download. Please, consider the Copyright. To get a short idea what is the benefit of neural networks have a look at page Neural Networks.

Overview

• Neural Networks
• Multilayer Perceptron
• Download
• Installation
• Examples
• Copyright

Versions and Change-Log

Version 2.0.2 by Thomas Wien (2008-01-14) Download

• Client-Server model for distributed applications
• Calculating total network error for csv logging

Version 2.0.1 by Thomas Wien (2008-01-06)

• Separation of classes to several files
• Version control by Subversion
• Performance issues
• Graphical output of neural network topology
• Logging of weights to csv file

Version 2.0.0 by Thomas Wien (2007-12-17)

• PHP 5.x support
• PHPDoc documentation
• Momentum support
• Avoiding network overfitting
• Linear / binary output
• ANN_InputValue + ANN_OutputValue classes
• Exceptions
• Threshold function
• Hyperbolic tangent transfer function
• Several performance issues
• Avoiding array_keys() & srand() due to performance
• Changes in saving and loading network
• Printing network details to browser
• Fixing bug: initializing inputs to all hidden layers
• Fixing bug: training for first hidden layer was skipped

Version 1.0 by Eddy Young (2002)

• Initial version

Todo

• Examples
• ANN_InputArray + ANN_OutputArray
• Performance check depending on host system
• Support for dynamic learning rate
• Automatic epoch determination
• Automatic output type detection
• Shuffling input patterns each epoch instead of randomized pattern access
• Wiki: More details to installation and use
• Wiki: Project specific logo ( Done! )
• PHPDoc: More details to documentation