kohen_example_not_sofm.cpp

BP神经网络算法的VC＋源码

/*
    nn-utility (Provides neural networking utilities for c++ programmers)
    Copyright (C) 2003 Panayiotis Thomakos

    This library is free software; you can redistribute it and/or
    modify it under the terms of the GNU Lesser General Public
    License as published by the Free Software Foundation; either
    version 2.1 of the License, or (at your option) any later version.

    This library is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
    Lesser General Public License for more details.
*/
//To contact the author send an email to [e-mail]

/*Demonstrates a non-Self-Organizing Feature Map that learns four letters*/

#include <nn-utility.h>
using namespace nn_utility;

//create a bitmap handler
BITMAP<float> *bit = new BITMAP<float>( "bitmap.txt" );
//define the VECTOR to load the bitmap letters
nn_utility_functions<float>::VECTOR letters[4];
//define a global classify layer
KOHEN *classify;

//overload and define floating-point nn-utility-functions
class kohen_example : public nn_utility_functions<float>{
public:
	typedef float VECTOR[NN_UTIL_SIZE];
	void GetInput( int interation, VECTOR &send, VECTOR &target ){
		CopyVector( send, letters[interation % 4], 256 );
		classify->radius = interation % 4;	
	}
}derived; //global derived

//see kohen_example.cpp
void SetRandomWeights( KOHEN **in, int row, int col ){
	for ( int i = 0; i < row; i++ ){
		for ( int e = 0; e < col; e++ ){
			float it = rand() % 10;
			(*in)->matrix[i][e] = it/100*( (rand() % 2) == 0 ? -1 : 1 );
		}
	}
}

int main(){

	//read the bitmap
	for ( int i = 0; i < 4; i++ )
		bit->readbitmap( letters[i], i );
	
	//define KOHEN, not KOHEN_SOFM
	//the rest of this file mimicks kohen_example.cpp, open
	//that file to see the remaining comments.
	classify = new KOHEN();
	classify->define( 256,9 );
	SetRandomWeights( &classify, 256,9 );
	
	nn_utility_functions<float>::VECTOR FINAL;
	layer<float> *ppClassify = classify;

	derived.train( &ppClassify, 4, 1.0F, false );

	cout << '\n';
	for ( int go = 0; go < 4; go++ ){
		classify->FeedForward( letters[go], FINAL );
		cout << go << " Original Classification: ";
		derived.PrintVector( FINAL, 9 );

		bit->noise( letters[go], 256, 1, 5 );
		classify->FeedForward( letters[go], FINAL );
		cout << go << " Noisy Classification   : ";
		derived.PrintVector( FINAL, 9 );
	}

	cout << '\n';
	return 0;
}