 |
|
Innovation award
 Nominee: 1x |
This class can be used to implement neural networks using back propagation.
It can setup a neural network work with a given number of layers.
The class takes a data set and a test output data set and runs the neural network using back propagation to to adjust weights based on network errors.
|
|
| Name: |
Back Propagation Scale |
| Base name: |
back-propagation |
| Description: |
Implement neural networks using back propagation |
| Version: |
- |
| PHP version: |
3.0 |
| License: |
Free For Educational Use |
| All time users: |
823 users |
| All time rank: |
3687 |
| Week users: |
3 users |
| Week rank: |
952  |
| |
|
 March 2010
Number 2
Prize: One book of choice by Apress |
Back propagation is a well known algorithm to implement neural networks.
It works by self-adjusting the weights of each neuron by propagating from the output to the input weights by evaluating the difference between the expected results and the current results during the training phase.
This class provides a PHP implementation of the back propagation algorithm.
Manuel Lemos |
| Not yet rated by the users |
| |
Applications that use this class |
|
|
No application links were specified for this class.

If you know an application of this package, send a message to the
author to add a link here.
| |
Files |
|
|