RadialBasisNetwork Class Reference

A Radial Basis Function Neural Network. More...

#include <RadialBasisNetwork.h>

Inheritance diagram for RadialBasisNetwork:

[legend]Collaboration diagram for RadialBasisNetwork:

[legend]List of all members.

Public Member Functions
	RadialBasisNetwork (int inputs, int centers, int outputs)
	Creates a Radial basis function network.
	RadialBasisNetwork (const char *filename)
	Loads a network from a text file.
	RadialBasisNetwork (RadialBasisNetwork &srcNet)
	Copy constructor, NOT YET IMPLEMENTED.
virtual	~RadialBasisNetwork ()
virtual void	setCenter (uint i, Vector &center)
	Sets the ith center point to the given point.
virtual void	setCenter (uint i, real *center)
	Sets the ith center point to the given point.
virtual Vector	getCenter (int i) const
	Returns the point corresponding to the ith center.
virtual uint	getCenterCount () const
	The number of centers in the network.
virtual void	setBias (uint i, real bias)
	Sets the bias of the ith output.
virtual real	getBias (uint i) const
	Returns the bias of the ith output.
virtual void	removeBias (uint i)
	Prevents the ith output from having any bias.
virtual void	setWeight (int center, int output, real weight)
	Sets the weight between the given center and output.
virtual real	getWeight (int center, int output) const
	Returns the weight of the link between the given center and output.
virtual Vector	getOutput (Vector &input)
	Returns the output of the network for the given input.
virtual Vector	getOutput (real *input)
	Wrapper function to allow getOutput() to work for an array of real as input as well.
void	setCenterActivationFunction (ActivationFunction f, ActivationFunction df)
	Sets the activation function of the center neurons.
void	trainWeights (TrainingSet &T)
	Trains the weights of the network, centers are kept fixed.
virtual const char *	getClassName () const
	Returns "RadialBasisNetwork".
virtual void	save (const char *filename)
	Save the network to a text file.
Protected Attributes
int	_nCenters
	Number of centers in the network.
InputLayer *	_inputLayer
	Layer of input. Each member is an InputNeuron.
Layer *	_centerLayer
	Layer of centers, each member is a CenterNEuron.
Layer *	_outputLayer
	Layer of output, each member if a SimpleNeuron.

---

Detailed Description

A Radial Basis Function Neural Network.

The network consists of a layer of N-inputs, then h-(N-dimensional) centers, and some outputs. The default activation function for the centers is gaussian(), which is the gaussian distribution function with sigma = 1. If you want to change that then you'll have to write your own activation function and change it with setCenterActivationFunction(). The output neurons use the identity() function as the activation function, thus the output is simply the weighted sum of the outputs of the centers.

There are atleast two ways to train a radial basis network.

One involves fixed centers and training the weights only in order to minimize the error over a training set. The other involves using the gradient descent rule to adjust both centers and weights. Currently only the former is implemented in annie using trainWeights().

See also:

trainWeights

Todo:

Implement gradient-descent rule based updation of centers and weights

The copy constructor

---

Constructor & Destructor Documentation

RadialBasisNetwork (  int  inputs, int  centers, int  outputs )

Creates a Radial basis function network. All the outputs will have a bias. Parameters: inputs  Number of inputs taken in by the network centers  Number of centers the network has. Each center will be an inputs-dimensional point outputs  The number of outputs given by the neuron. All of them will have a bias

RadialBasisNetwork (  const char *  filename  )

Loads a network from a text file. See also: save Parameters: filename  Name of the file from which to load network structure Exceptions: Exception  On any error

RadialBasisNetwork (  RadialBasisNetwork &  srcNet  )

Copy constructor, NOT YET IMPLEMENTED.

virtual ~RadialBasisNetwork (   )  [virtual]

---

Member Function Documentation

virtual real getBias (  uint  i  )  const [virtual]

Returns the bias of the ith output. Parameters: i  The index of the output (0<=i<getOutputCount()). Returns: The bias of the output. If there is no bias, it returns 0.0

virtual Vector getCenter (  int  i  )  const [virtual]

Returns the point corresponding to the ith center. Parameters: i  The center whose point is wanted Returns: The getInputCount() dimensional point corresponding to the ith center

virtual uint getCenterCount (   )  const [virtual]

The number of centers in the network.

virtual const char* getClassName (   )  const [virtual]

Returns "RadialBasisNetwork". Implements Network.

virtual Vector 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 Network.

virtual Vector 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

virtual real getWeight (  int  center, int  output )  const [virtual]

Returns the weight of the link between the given center and output. Parameters: center  Index of the center (0<=center<getCenterCount()). output  Index of the output (0<=output<getOutputCount()). Exceptions: Exception  if any of the parameters given is invalid

virtual void removeBias (  uint  i  )  [virtual]

Prevents the ith output from having any bias. Parameters: i  The index of the output (0<=i<getOutputCount()). Exceptions: Exception  if the index given is invalid

virtual void save (  const char *  filename  )  [virtual]

Save the network to a text file.

virtual void setBias (  uint  i, real  bias )  [virtual]

Sets the bias of the ith output. Parameters: i  The index of the output (0<=i<getOutputCount()). bias  The bias to be given to that output. Exceptions: Exception  if that neuron isn't allowed to be biased.

virtual void setCenter (  uint  i, real *  center )  [virtual]

Sets the ith center point to the given point. Parameters: i  The center that is to be changed center  The getInputCount() dimensional point

virtual void setCenter (  uint  i, Vector &  center )  [virtual]

Sets the ith center point to the given point. Parameters: i  The center that is to be changed center  The getInputCount() dimensional point

void setCenterActivationFunction (  ActivationFunction  f, ActivationFunction  df )

Sets the activation function of the center neurons. (The activation function is gaussian by default) Parameters: f  The activation function to be used. df  The derivation of the activation function, used in gradient descent training

virtual void setWeight (  int  center, int  output, real  weight )  [virtual]

Sets the weight between the given center and output. Parameters: center  Index of the center (0<=center<getCenterCount()). output  Index of the output (0<=output<getOutputCount()). weight  The weight to give to the link between the center and output. Exceptions: Exception  if any of the parameters given is invalid

void trainWeights (  TrainingSet &  T  )

Trains the weights of the network, centers are kept fixed. Parameters: T  The TrainingSet from which input/desired-output pairs will be obtained

---

Member Data Documentation

Layer* _centerLayer [protected]

Layer of centers, each member is a CenterNEuron.

InputLayer* _inputLayer [protected]

Layer of input. Each member is an InputNeuron.

int _nCenters [protected]

Number of centers in the network. If you plan to extend this class, then the onus of keeping this value consistent lies on you

Layer* _outputLayer [protected]

Layer of output, each member if a SimpleNeuron.

---

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

• RadialBasisNetwork.h

---