HopfieldNetwork Class Reference

A "standard" incarnation of the Hopfield network usable form most purposes. More...

#include <HopfieldNetwork.h>

Inheritance diagram for HopfieldNetwork:

[legend]Collaboration diagram for HopfieldNetwork:

[legend]List of all members.

Public Member Functions
	HopfieldNetwork (uint size, bool bias=false, bool bipolar=true)
	HopfieldNetwork (const char *filename)
	Loads a Hopfield network from a file.
	~HopfieldNetwork ()
	Cleans up memory by getting rid of the weight matrix.
virtual void	save (const std::string &filename)
	Saves the network to a file.
virtual void	setWeight (uint i, uint j, real weight)
	Sets the weight between the ith and jth neuron.
virtual Matrix	getWeightMatrix ()
	Returns a copy of the weight matrix that is used by this network.
virtual void	addPattern (int pattern[])
	Adds a pattern to the network by making suitable adjustments to the weight matrix.
virtual uint	getPatternCount ()
	The number of patterns that the network has been instructed to store This will be the same as the number of calls to addPattern.
Protected Member Functions
virtual real	getWeight (uint from, uint to) const
Protected Attributes
Matrix *	_weightMatrix
	The weight matrix of the network.

---

Detailed Description

A "standard" incarnation of the Hopfield network usable form most purposes.

It will have problems with large number of neurons (because the weights for 'em need ^2 memory)

---

Constructor & Destructor Documentation

HopfieldNetwork (  uint  size, bool  bias = false, bool  bipolar = true )

HopfieldNetwork (  const char *  filename  )

Loads a Hopfield network from a file. See also: save Parameters: filename  The name of the filename to load the network from Exceptions: Exception  on any error

~HopfieldNetwork (   )

Cleans up memory by getting rid of the weight matrix.

---

Member Function Documentation

virtual void addPattern (  int  pattern[]  )  [virtual]

Adds a pattern to the network by making suitable adjustments to the weight matrix. Parameters: pattern  The bipolar pattern (of getSize() length) to be stored Exceptions: Exception  If the given pattern is not bipolar (i.e., consisting of only -1s and 1s) and the network is designed for bipolar patters or if the pattern does not consist of 0s and 1s

virtual uint getPatternCount (   )  [virtual]

The number of patterns that the network has been instructed to store This will be the same as the number of calls to addPattern. See also: addPattern

virtual real getWeight (  uint  from, uint  to )  const [protected, virtual]

Implements HopfieldBase.

virtual Matrix getWeightMatrix (   )  [virtual]

Returns a copy of the weight matrix that is used by this network.

virtual void save (  const std::string &  filename  )  [virtual]

Saves the network to a file. Todo: Implement this! Parameters: filename  The name of the file to store the network into so that it can be loaded from there later Reimplemented from HopfieldBase.

virtual void setWeight (  uint  i, uint  j, real  weight )  [virtual]

Sets the weight between the ith and jth neuron. Since the weights are symmetruc, the weight between neuron i and neuron j will be the same as the weight between neuron j and neuron i, which will be the same as the weight supplied. Parameters: i  The ith neuron j  The jth neuron weight  The weight of the link (i,j) and (j,i) Implements HopfieldBase.

---

Member Data Documentation

Matrix* _weightMatrix [protected]

The weight matrix of the network.

---

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

• HopfieldNetwork.h

---