Download: Difference between revisions

From Artificial Neural Network for PHP
No edit summary
No edit summary
Line 35: Line 35:


'''Documentation'''
'''Documentation'''

* [http://ann.thwien.de/phpdoc/ Documentation (HTML online)]


* [http://ann.thwien.de/downloads/ann205_phpdoc.zip Documentation (HTML download, zip compressed)]
* [http://ann.thwien.de/downloads/ann205_phpdoc.zip Documentation (HTML download, zip compressed)]
Line 55: Line 53:
* [http://ann.thwien.de/downloads/ann204.zip Download - ann204.zip] (25 KB)
* [http://ann.thwien.de/downloads/ann204.zip Download - ann204.zip] (25 KB)
* [http://ann.thwien.de/downloads/ann204.tar.gz Download - ann204.tar.gz] (29 KB)
* [http://ann.thwien.de/downloads/ann204.tar.gz Download - ann204.tar.gz] (29 KB)

'''Documentation (online)'''

* [http://ann.thwien.de/phpdoc/ Documentation (HTML online)]


'''Change-Log'''
'''Change-Log'''

Revision as of 14:41, 28 December 2008

ANN - Artificial Neural Network for PHP 5.x

Current stable version of ANN implementation for PHP 5.x is version 2.0.6. 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 2.0.6 (2008-12-18) stable

Author: Thomas Wien

Documentation

Change-Log

  • Printing network details of output differences to their desired values
  • Complete rewritten code standard of variables
  • New class ANN_Values for defining input and output values
  • Code examples to phpdoc
  • Internal math precision defaults to 5

Version 2.0.5 (2008-12-16) obsolete

Author: Thomas Wien

Documentation

Change-Log

  • Adjustable output error tolerance between 0 and 10 per cent
  • Internal rounding of floats for performance issues
  • Loading class for all ANN classes (SPL autoload)
  • Renaming filename of ANN_Maths class
  • Improving code standard
  • Fixing bug: Comparision in ANN_InputValue and ANN_OutputValue

Version 2.0.4 (2008-01-27) obsolete

Author: Thomas Wien

Change-Log

  • Weight decay
  • QuickProp algorithm (experimental)
  • RProp algorithm (experimental)
  • Linear saturated activation function (experimental)
  • Individual learning rate algorithm (experimental)
  • Reducing of overfitting (no training if input pattern produces desired output)
  • Increasing performance on activation
  • Increasing performance on testing all patterns to their desired outputs
  • Increasing performance on calculating hidden deltas
  • Increasing performance by defining layer relation by construction
  • More details to printNetwork()
  • Fixing bug: learning rate is not part of saved delta value

Version 2.0.3 (2008-01-17) obsolete

Author: Thomas Wien

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()
  • Extending display of network details

Version 2.0.2 (2008-01-14) obsolete

Author: Thomas Wien

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

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

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