Download

ANN - Artificial Neural Network for PHP 5.x

Current stable version of ANN implementation for PHP 5.x is version 2.0.3. Go to Installation section to get information on how to implement these PHP libraries into your project.

Requirements

The latest implementation requires a php environment running PHP 5.2.x or above. If using the client-server mechanism of the network class, the curl extension must be available on the client host which connects to an ANN server. If using class ANN_NetworkGraph GD library with png support must be installed.

Version 2.0.3 (2008-01-17) stable

Author: Thomas Wien

• Download - ann203.zip (22 KB)
• Download - ann203.tar.gz (20 KB)

Documentation (online)

• Documentation (HTML online)

Change-Log

• Support for dynamic learning rate
• Automatic epoch determination
• Automatic output type detection
• Shuffling input patterns each epoch instead of randomized pattern access
• Bug fix: runtime error on call of setMomentum()
• Logging of network errors
• Logging on each epoch instead of each training step
• Avoiding distributed internal calls of setMomentum() and setLearningRate()

Version 2.0.2 (2008-01-14) obsolete

Author: Thomas Wien

• Download - ann202.zip (21 KB)
• Download - ann202.tar.gz (17 KB)

Documentation (online)

• Documentation (HTML online)

Change-Log

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

Version 2.0.1 (2008-01-06) obsolete

Author: Thomas Wien

• Download - ann201.zip (19 KB)
• Download - ann201.tar.gz (16 KB)

Documentation (online)

• Documentation (HTML online)

Change-Log

• 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 (2007-12-17) obsolete

Author: Thomas Wien

• Download - ann200.zip (6 KB)
• Download - ann200.tar.gz (6 KB)

Documentation (online)

• Documentation (HTML online)

Change-Log

• PHP 5.x support
• PHPDoc documentation
• Momentum support
• Avoiding network overfitting
• Linear / binary output
• ANN_InputValue + ANN_OutputValue classes
• Exceptions
• Threshold function
• Tangens hyperbolicus 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 (2002)

Author: Eddy Young

Project page on freebsd.mu

Change-Log

• Initial version