Difference between revisions of "Main Page"

From Artificial Neural Network for PHP
 
Line 1: Line 1:
<big>'''MediaWiki has been successfully installed.'''</big>
+
<big>'''ANN - Artificial Neural Network for PHP 5.x'''</big>
   
  +
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 changes on this implementation are done by ''Thomas Wien'' in 2007.
Consult the [http://meta.wikimedia.org/wiki/Help:Contents User's Guide] for information on using the wiki software.
 
   
  +
----
== Getting started ==
 
   
  +
'''Version 1.0 by Eddy Young''' (2002)
* [http://www.mediawiki.org/wiki/Manual:Configuration_settings Configuration settings list]
 
  +
* [http://www.mediawiki.org/wiki/Manual:FAQ MediaWiki FAQ]
 
  +
* Initial version
* [http://lists.wikimedia.org/mailman/listinfo/mediawiki-announce MediaWiki release mailing list]
 
  +
  +
'''Version 2.0 by Thomas Wien''' (17.12.2007)
  +
  +
* PHP 5.x support
  +
* Momentum
  +
* linear / binary Output
  +
* ANN_InputValue + ANN_OutputValue classes
  +
* Exceptions
  +
* Threshold function
  +
* tangens hyperbolicus transfer function
  +
* several performance issues
  +
* avoiding array_keys & srand
  +
* 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
  +
  +
== Overview ==
  +
  +
* [[Download]]
  +
* [[Installation]]
  +
* [[Copyright]]

Revision as of 20:03, 17 December 2007

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 changes on this implementation are done by Thomas Wien in 2007.


Version 1.0 by Eddy Young (2002)

  • Initial version

Version 2.0 by Thomas Wien (17.12.2007)

  • PHP 5.x support
  • Momentum
  • linear / binary Output
  • ANN_InputValue + ANN_OutputValue classes
  • Exceptions
  • Threshold function
  • tangens hyperbolicus transfer function
  • several performance issues
  • avoiding array_keys & srand
  • 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

Overview