---

annie::MultiLayerNetwork Class Reference

#include <MultiLayerNetwork.h>

Inheritance diagram for annie::MultiLayerNetwork:

List of all members.

Public Methods
	MultiLayerNetwork (int inputs)
	MultiLayerNetwork (MultiLayerNetwork &srcNet)
	Copy constructor, NOT YET IMPLEMENTED. More...
	MultiLayerNetwork (const char *filename)
virtual	~MultiLayerNetwork ()
virtual void	addLayer (int size)
	Adds a layer of the given size to the network. This new layer becomes the output layer. More...
virtual void	connectLayer (int srcLayer)
virtual void	connect (int srcLayer, int srcNrn, int destNrn)
virtual void	connect (int srcLayer, int srcNrn, int destNrn, real weight)
virtual void	setBias (int layer, int nrn, real bias)
virtual int	getLayerCount ()
	The number of layers in the network (does not count the input layer as a layer). More...
virtual VECTOR	getOutput (VECTOR &input)
virtual VECTOR	getOutput (real *input)
virtual void	train (TrainingSet &T, int epochs, real learningRate, real momentum=0.0)
virtual void	train (TrainingSet &T, int epochs, real learningRate, real momentum, bool verbose)
virtual void	save (const char *filename)
virtual void	setActivationFunction (int layer, ActivationFunction f, ActivationFunction df)
virtual const char *	getClassName ()
	Returns "MultiLayerNetwork". More...
Protected Methods
InputLayer *	_inputLayer ()
	The input layer. More...
Layer *	_outputLayer ()
	The output layer. More...
Protected Attributes
int	_nLayers
std::vector< Layer * >	_layers
	The layers. More...

---

Detailed Description

Abstraction of a multi-layer perceptron network. Basically, layers of SimpleNeurons constitute this network. Training is done using the backpropagation technique which uses the gradient descent method.

The labels of the layers start from 0 (for the input layer) and then keep moving on. The labels of neurons in the layers is = <layer label>*Layer::MAX_LAYER_SIZE + <neuron index in layer>

All neurons in the layers are allowed to have a bias.

Todo:

The copy constructor

---

Constructor & Destructor Documentation

annie::MultiLayerNetwork::MultiLayerNetwork (  int    inputs )

Create a multi-layer network. Parameters: inputs  The number of inputs taken in by the network

annie::MultiLayerNetwork::MultiLayerNetwork (  MultiLayerNetwork &    srcNet )

Copy constructor, NOT YET IMPLEMENTED.

annie::MultiLayerNetwork::MultiLayerNetwork (  const char *    filename )

Loads a multi-layer network from the given filename. Parameters: filename  The name of the file from which to load the network Exceptions: Exception  On any error

virtual annie::MultiLayerNetwork::~MultiLayerNetwork (    )  [virtual]

---

Member Function Documentation

InputLayer* annie::MultiLayerNetwork::_inputLayer (    )  [protected]

The input layer.

Layer* annie::MultiLayerNetwork::_outputLayer (    )  [protected]

The output layer.

virtual void annie::MultiLayerNetwork::addLayer (  int    size )  [virtual]

Adds a layer of the given size to the network. This new layer becomes the output layer. Reimplemented in annie::TwoLayerNetwork.

virtual void annie::MultiLayerNetwork::connect (  int    srcLayer, int    srcNrn, int    destNrn, real    weight )  [virtual]

Connects two neurons, with the weight provided. Parameters: srcLayer  The index of the layer in which the source neuron lies srcNrn  The index of the source neuron in the source layer destNrn  The index of the destination neuron (will be in the layer with index srcLayer+1) weight  The weight of the link Exceptions: Exception  On any invalid argument values

virtual void annie::MultiLayerNetwork::connect (  int    srcLayer, int    srcNrn, int    destNrn )  [virtual]

Connects two neurons, with random weight Parameters: srcLayer  The index of the layer in which the source neuron lies srcNrn  The index of the source neuron in the source layer destNrn  The index of the destination neuron (will be in the layer with index srcLayer+1) Exceptions: Exception  On any invalid argument values

virtual void annie::MultiLayerNetwork::connectLayer (  int    srcLayer )  [virtual]

Completely connects the given layer with the layer below it, i.e., all neurons in the given layer will give their output to all the neurons in the layer below. Weights are random. Parameters: srcLayer  The index of the source layer Exceptions: Exception  If the layer index provided is invalid

virtual const char* annie::MultiLayerNetwork::getClassName (    )  [virtual]

Returns "MultiLayerNetwork". Implements annie::Network. Reimplemented in annie::TwoLayerNetwork.

virtual int annie::MultiLayerNetwork::getLayerCount (    )  [virtual]

The number of layers in the network (does not count the input layer as a layer).

virtual VECTOR annie::MultiLayerNetwork::getOutput (  real *    input )  [virtual]

Wrapper function to allow getOutput() to work for an array of real as input as well. Does exactly the same thing as Network::getOutput(real*). Reimplemented from annie::Network.

virtual VECTOR annie::MultiLayerNetwork::getOutput (  VECTOR &    input )  [virtual]

Returns the output of the network for the given input. Parameters: input  A vector of getDimension() reals Returns: The corresponding output of the network Implements annie::Network.

virtual void annie::MultiLayerNetwork::save (  const char *    filename )  [virtual]

Saves the network to the given filename. The file is a simple text file, open it up in a text editor to see the format, quite simple Parameters: filename  The name of the file to save the network in. Implements annie::Network.

virtual void annie::MultiLayerNetwork::setActivationFunction (  int    layer, ActivationFunction    f, ActivationFunction    df )  [virtual]

Sets the activation function used by the neurons in the provided layer. Parameters: layer  The layer whose activation function is to be changed. layer>0 (as input neurons don't have any activation function) and layer<getLayerCount() f  The activation function to be used df  The derivative of the activation function to be used. Required for training. Exceptions: Exception  if an invalid layer is given

virtual void annie::MultiLayerNetwork::setBias (  int    layer, int    nrn, real    bias )  [virtual]

Sets the bias of the given neuron. Parameters: layer  The index of the layer in which the neuron lies nrn  The index of the neuron in the layer bias  The bias to be given to the neuron

virtual void annie::MultiLayerNetwork::train (  TrainingSet &    T, int    epochs, real    learningRate, real    momentum, bool    verbose )  [virtual]

Trains the network with data from the given TrainingSet using the backpropagation algorithm. Parameters: T  The TrainingSet containing input/desired-output vector pairs epochs  The number of epochs to train the network. An epoch is a single iteration through all input/desired-output vector pairs in T. learningRate  The learning rate to be used for weight updation momentum  The momentum factor to be used during weight updation verbose  If true, prints the current epoch number onto stdout, if false no such status information is given.

virtual void annie::MultiLayerNetwork::train (  TrainingSet &    T, int    epochs, real    learningRate, real    momentum = 0.0 )  [virtual]

Trains the network with data from the given TrainingSet using the backpropagation algorithm. Parameters: T  The TrainingSet containing input/desired-output vector pairs epochs  The number of epochs to train the network. An epoch is a single iteration through all input/desired-output vector pairs in T. learningRate  The learning rate to be used for weight updation momentum  The momentum factor to be used during weight updation. 0 by default.

---

Member Data Documentation

std::vector<Layer *> annie::MultiLayerNetwork::_layers [protected]

The layers.

int annie::MultiLayerNetwork::_nLayers [protected]

Number of layers in the network. If you derive your own network from this class, the onus of keeping _nLayers consistent lies on you!

---

The documentation for this class was generated from the following file:

• MultiLayerNetwork.h

---