Class NeuralNetwork

Multi-layer Neural Network in PHP

Loosely based on source code by Phil Brierley, that was translated into PHP by 'dspink' in sep 2005

Algorithm was obtained from the excellent introductory book "Artificial Intelligence - a guide to intelligent systems" by Michael Negnevitsky (ISBN 0-201-71159-1)

Example: learning the 'XOR'-function

// Create a new neural network with 3 input neurons,
// 4 hidden neurons, and 1 output neuron
$n = new NeuralNetwork(3, 4, 1);
$n->setVerbose(false);

// Add test-data to the network. In this case,
// we want the network to learn the 'XOR'-function
$n->addTestData(array (-1, -1, 1), array (-1));
$n->addTestData(array (-1,  1, 1), array ( 1));
$n->addTestData(array ( 1, -1, 1), array ( 1));
$n->addTestData(array ( 1,  1, 1), array (-1));

// we try training the network for at most $max times
$max = 3;

// train the network in max 1000 epochs, with a max squared error of 0.01
while (!($success = $n->train(1000, 0.01)) && ++$i<$max) {
    echo "Round $i: No success...<hr />";
}

// print a message if the network was succesfully trained
if ($success) {
    $epochs = $n->getEpoch();
    echo "Success in $epochs training rounds!<hr />";
}

// in any case, we print the output of the neural network
echo "<h2>End result</h2>";
for ($i = 0; $i < count($n->trainInputs); $i ++) {
    $output = $n->calculate($n->trainInputs[$i]);
    echo "<br />Testset $i; ";
    echo "expected output = (".implode(", ", $n->trainOutput[$i]).") ";
    echo "output from neural network = (".implode(", ", $output).")\n";
}

The resulting output could for example be something along the following lines:

Success in 719 training rounds!
Testset 0; expected output = (-1) output from neural network = (-0.986415991978)
Testset 1; expected output = (1) output from neural network = (0.992121412998)
Testset 2; expected output = (1) output from neural network = (0.992469534962)
Testset 3; expected output = (-1) output from neural network = (-0.990224120384)

...which indicates the network has learned the task.

License: BSD License
Author: E. Akerboom
Author: Tremani, Delft, The Netherlands
Version: 1.1
Since: feb 2007
Located at class_neuralnetwork.php

Methods summary

`public`	# `__construct( array $nodeCount )` Creates a neural network. Creates a neural network. Example: // create a network with 4 input nodes, 10 hidden nodes, and 4 output nodes $n = new NeuralNetwork(4, 10, 4); // create a network with 4 input nodes, 1 hidden layer with 10 nodes, // another hidden layer with 10 nodes, and 4 output nodes $n = new NeuralNetwork(4, 10, 10, 4); // alternative syntax $n = new NeuralNetwork(array(4, 10, 10, 4)); Parameters `$nodeCount` The number of nodes in the consecutive layers.
`public`	# `export( )` Exports the neural network Exports the neural network Returns array
`public`	# `import( array $nn_array )` Import a neural network Import a neural network Parameters `$nn_array` An array of the neural network parameters
`public`	# `setLearningRate( array $learningRate )` Sets the learning rate between the different layers. Sets the learning rate between the different layers. Parameters `$learningRate` An array containing the learning rates [range 0.0 - 1.0]. The size of this array is 'layerCount - 1'. You might also provide a single number. If that is the case, then this will be the learning rate for the whole network.
`public float`	# `getLearningRate( integer $layer )` Gets the learning rate for a specific layer Gets the learning rate for a specific layer Parameters `$layer` The layer to obtain the learning rate for Returns float The learning rate for that layer
`public`	# `setMomentum( float $momentum )` Sets the 'momentum' for the learning algorithm. The momentum should accelerate the learning process and help avoid local minima. Sets the 'momentum' for the learning algorithm. The momentum should accelerate the learning process and help avoid local minima. Parameters `$momentum` The momentum. Must be between 0.0 and 1.0; Usually between 0.5 and 0.9
`public float`	# `getMomentum( )` Gets the momentum. Gets the momentum. Returns float The momentum
`public mixed`	# `calculate( array $input )` Calculate the output of the neural network for a given input vector Calculate the output of the neural network for a given input vector Parameters `$input` The vector to calculate Returns mixed The output of the network
`protected float`	# `activation( float $value )` Implements the standard (default) activation function for backpropagation networks, the 'tanh' activation function. Implements the standard (default) activation function for backpropagation networks, the 'tanh' activation function. Parameters `$value` The preliminary output to apply this function to Returns float The final output of the node
`protected`	# `derivativeActivation( float $value )` Implements the derivative of the activation function. By default, this is the inverse of the 'tanh' activation function: 1.0 - tanh($value)tanh($value); Implements the derivative of the activation function. By default, this is the inverse of the 'tanh' activation function: 1.0 - tanh($value)tanh($value); Parameters `$value` 'X' Returns $float
`public NetworkGraph`	# `networkgraph( )` Calculates the parameters for the NetworkGraph and returns it Calculates the parameters for the NetworkGraph and returns it Returns `NetworkGraph` NetworkGraph class
`public`	# `addTestData( array $input, array $output, integer $id = null )` Add a test vector and its output Add a test vector and its output Parameters `$input` An input vector `$output` The corresponding output `$id` (optional) An identifier for this piece of data
`public array`	# `getTestDataIDs( )` Returns the identifiers of the data used to train the network (if available) Returns the identifiers of the data used to train the network (if available) Returns array An array of identifiers
`public`	# `addControlData( array $input, array $output, integer $id = null )` Add a set of control data to the network. Add a set of control data to the network. This set of data is used to prevent 'overlearning' of the network. The network will stop training if the results obtained for the control data are worsening. The data added as control data is not used for training. Parameters `$input` An input vector `$output` The corresponding output `$id` (optional) An identifier for this piece of data
`public array`	# `getControlDataIDs( )` Returns the identifiers of the control data used during the training of the network (if available) Returns the identifiers of the control data used during the training of the network (if available) Returns array An array of identifiers
`public`	# `showWeights( boolean $force = false )` Shows the current weights and thresholds Shows the current weights and thresholds Parameters `$force` Force the output, even if the network is setVerbose() not verbose.
`public`	# `setVerbose( boolean $isVerbose )` Determines if the neural network displays status and error messages. By default, it does. Determines if the neural network displays status and error messages. By default, it does. Parameters `$isVerbose` 'true' if you want to display status and error messages, 'false' if you don't
`public boolean`	# `isVerbose( )` Returns whether or not the network displays status and error messages. Returns whether or not the network displays status and error messages. Returns boolean 'true' if status and error messages are displayed, 'false' otherwise
`public boolean`	# `load( string $filename )` Loads a neural network from a file saved by the 'save()' function. Clears the training and control data added so far. Loads a neural network from a file saved by the 'save()' function. Clears the training and control data added so far. Parameters `$filename` The filename to load the network from Returns boolean 'true' on success, 'false' otherwise
`public boolean`	# `save( string $filename )` Saves a neural network to a file Saves a neural network to a file Parameters `$filename` The filename to save the neural network to Returns boolean 'true' on success, 'false' otherwise
`public`	# `clear( )` Resets the state of the neural network, so it is ready for a new round of training. Resets the state of the neural network, so it is ready for a new round of training.
`public boolean`	# `train( integer $maxEpochs = 500, float $maxError = 0.01 )` Start the training process Start the training process Parameters `$maxEpochs` The maximum number of epochs `$maxError` The maximum squared error in the training data Returns boolean 'true' if the training was successful, 'false' otherwise
`public integer`	# `getEpoch( )` Gets the number of epochs the network needed for training. Gets the number of epochs the network needed for training. Returns integer The number of epochs.
`public float`	# `getErrorTrainingSet( )` Gets the squared error between the desired output and the obtained output of the training data. Gets the squared error between the desired output and the obtained output of the training data. Returns float The squared error of the training data
`public float`	# `getErrorControlSet( )` Gets the squared error between the desired output and the obtained output of the control data. Gets the squared error between the desired output and the obtained output of the control data. Returns float The squared error of the control data
`public boolean`	# `getTrainingSuccessful( )` Determines if the training was successful. Determines if the training was successful. Returns boolean 'true' if the training was successful, 'false' otherwise
`public`	# `initWeights( )` Randomise the weights in the neural network Randomise the weights in the neural network

Properties summary

`protected array`	`$nodeCount`	# `array ()`
`protected array`	`$nodeValue`	# `array ()`
`protected array`	`$nodeThreshold`	# `array ()`
`protected array`	`$edgeWeight`	# `array ()`
`protected array`	`$learningRate`	# `array (0.1)`
`protected integer`	`$layerCount`	# `0`
`protected array`	`$previousWeightCorrection`	# `array ()`
`protected float`	`$momentum`	# `0.8`
`protected boolean`	`$isVerbose`	# `true`
`protected boolean`	`$weightsInitialized`	# `false`
`public array`	`$trainInputs`	# `array ()`
`public array`	`$trainOutput`	# `array ()`
`public array`	`$trainDataID`	# `array ()`
`public array`	`$controlInputs`	# `array ()`
`public array`	`$controlOutput`	# `array ()`
`public array`	`$controlDataID`	# `array ()`
`protected`	`$epoch`	#
`protected`	`$errorTrainingset`	#
`protected`	`$errorControlset`	#
`protected`	`$success`	#

Classes

Class NeuralNetwork

Methods summary

Parameters

Returns

Parameters

Parameters

Parameters

Returns

Parameters

Returns

Parameters

Returns

Parameters

Returns

Parameters

Returns

Returns

Parameters

Returns

Parameters

Returns

Parameters

Parameters

Returns

Parameters

Returns

Parameters

Returns

Parameters

Returns

Returns

Returns

Returns

Returns

Properties summary