view release on metacpan or  search on metacpan

examples/NeuralNet/NeuralNet.h  view on Meta::CPAN

/// \file NeuralNet.h
/// \brief Header file for simple 3 layer feed forward NeuralNet classes / DLL
/// 
/// \author Kyle Schlansker
/// \date August 2004
///////////////////////////////////////////////////////////////////////////


#include <iostream>
#include <cmath>
#include <string>
using namespace std;

#ifdef WIN32
#  ifdef NEURALNET_EXPORTS
#    define NEURALNET_API __declspec(dllexport)
#  else
#    define NEURALNET_API __declspec(dllimport)
#  endif
#else
#  define NEURALNET_API
#endif

#ifndef NEURAL_NET
#define NEURAL_NET


///
/// \class TransferFunction NeuralNet.h NeuralNet
/// \brief defines a transfer function object
/// 
class NEURALNET_API TransferFunction
{
    public:

        ///
        /// \fn TransferFunction(double val)
        /// \brief constructor
        /// \param val a double
        ///
        TransferFunction(double val = 1)
        {
        }


        ///
        /// \fn ~TransferFunction()
        /// \brief destructor
        ///
        virtual ~TransferFunction()
        {
        }


        /// 
        /// \fn virtual double compute()
        /// \brief computes the transfer function and returns result
        /// \param val a double
        /// \return double
        /// 
        virtual double compute(double val) = 0;


    protected:

        double m_value;        /// value on which to compute the transfer function
};



///
/// \class UnityGain NeuralNet.h NeuralNet
/// \brief defines a transfer function that passes its output as its input (good for input neurons)
///
class NEURALNET_API UnityGain : public TransferFunction
{
    public:
        
        ///
        /// \fn UnityGain(double val) 
        /// \brief constructor
        /// \param val a double
        ///
        UnityGain(double val = 1) : TransferFunction(val)
        {
        }


        ///
        /// \fn ~UnityGain()
        /// \brief destructor
        ///
        ~UnityGain()
        {
        }


        ///
        /// \fn compute(double val)
        /// \brief computes the transfer function by returning the input
        /// \return double
        ///
        double compute(double val)
        {
            return m_value = val;
        }
};



///
/// \class Logistic  NeuralNet.h NeuralNet
/// \brief defines the Logistic transfer function
///
class NEURALNET_API Logistic : public TransferFunction
{
    public:

examples/NeuralNet/NeuralNet.h  view on Meta::CPAN

        ///
        /// \fn void setWeight(int index, double weight)
        /// \brief sets the connection weight of connection at
        ///           index to weight
        /// \param index an int
        /// \param weight a double
        ///
        void setWeight(int index, double weight)
        {
            if(index >= 0 && index <= m_numConnections)
                m_weights[index] = weight;
        }


        ///
        /// \fn int numConnections()
        /// \brief returns the number of connections this Neuron has
        /// \return int
        ///
        int numConnections()
        {
            return m_numConnections;
        }



    protected:

        ///
        /// \fn void checkSize()
        /// \brief checks the size of the connection array for this Neuron.
        ///            if a connection needs to be added past the capacity, then
        ///            new connection array space is allocated.
        /// 
        void checkSize()
        {
            if( m_numConnections >= m_capacity )
            {
                m_capacity *= 2;
                Neuron **newNeuronArr = new Neuron*[m_capacity];
                double *newWeightArr = new double[m_capacity];

                for(int i = 0; i < m_numConnections; i++)
                {
                    newNeuronArr[i] = m_neurons[i];
                    newWeightArr[i] = m_weights[i];
                }

                delete [] m_neurons;
                delete [] m_weights;

                m_neurons = newNeuronArr;
                m_weights = newWeightArr;
            }
        }


        ///
        /// \fn double transferFunction(double val)
        /// \brief applies a transfer function to val and returns the result
        /// \param val a double
        /// \return double
        ///
        double transferFunc(double val)
        {
            return val;
        }


        int        m_numConnections;    /// number of connections to other Neurons
        int        m_capacity;        /// capacity of connection array
        Neuron **m_neurons;            /// connection array of pointers to other Neurons
        double *m_weights;            /// weight array of connections
        double    m_value;            /// value of this Neuron
        TransferFunction *xfer;        
};




/// 
/// \class Input NeuralNet.h NeuralNet
/// \brief Simulates an input neuron in a Neural net.  This class extends Neuron
///            but allows for its value to be set directly and it also overrides 
///            the virtual value function so that it returns its value directly 
///            rather than passing though a transfer function.
///
class NEURALNET_API Input : public Neuron
{
    public:


        ///
        /// \fn Input(double value)
        /// \brief constructor
        ///
        Input(double value = 0) : Neuron()
        {
            m_value = value;
        }


        ///
        /// \fn ~Input()
        /// \brief destructor
        ///
        virtual ~Input()
        {
        }


        ///
        /// \fn void setValue(double value)
        /// \brief sets the value of this input Neuron to value
        /// \param value a double
        ///
        void setValue(double value)
        {
            m_value = value;
        }