66

这是我在 ANSI C 中的感知器实现:

#include <stdio.h>
#include <stdlib.h>
#include <math.h>

float randomFloat()
{
    srand(time(NULL));
    float r = (float)rand() / (float)RAND_MAX;
    return r;
}

int calculateOutput(float weights[], float x, float y)
{
    float sum = x * weights[0] + y * weights[1];
    return (sum >= 0) ? 1 : -1;
}

int main(int argc, char *argv[])
{
    // X, Y coordinates of the training set.
    float x[208], y[208];

    // Training set outputs.
    int outputs[208];

    int i = 0; // iterator

    FILE *fp;

    if ((fp = fopen("test1.txt", "r")) == NULL)
    {
        printf("Cannot open file.\n");
    }
    else
    {
        while (fscanf(fp, "%f %f %d", &x[i], &y[i], &outputs[i]) != EOF)
        {
            if (outputs[i] == 0)
            {
                outputs[i] = -1;
            }
            printf("%f   %f   %d\n", x[i], y[i], outputs[i]);
            i++;
        }
    }

    system("PAUSE");

    int patternCount = sizeof(x) / sizeof(int);

    float weights[2];
    weights[0] = randomFloat();
    weights[1] = randomFloat();

    float learningRate = 0.1;

    int iteration = 0;
    float globalError;

    do {
        globalError = 0;
        int p = 0; // iterator
        for (p = 0; p < patternCount; p++)
        {
            // Calculate output.
            int output = calculateOutput(weights, x[p], y[p]);

            // Calculate error.
            float localError = outputs[p] - output;

            if (localError != 0)
            {
                // Update weights.
                for (i = 0; i < 2; i++)
                {
                    float add = learningRate * localError;
                    if (i == 0)
                    {
                        add *= x[p];
                    }
                    else if (i == 1)
                    {
                        add *= y[p];
                    }
                    weights[i] +=  add;
                }
            }

            // Convert error to absolute value.
            globalError += fabs(localError);

            printf("Iteration %d Error %.2f %.2f\n", iteration, globalError, localError);

            iteration++;
        }

        system("PAUSE");

    } while (globalError != 0);

    system("PAUSE");
    return 0;
}

我正在使用的训练集:数据集

我已经删除了所有不相关的代码。基本上它现在所做的就是读取test1.txt文件并将值从其中加载到三个数组中:x, y, outputs.

然后有一个感知器学习算法,由于某种原因,它没有收敛到 0(globalError应该收敛到 0),因此我得到了一个无限的 do while 循环。

当我使用较小的训练集(如 5 分)时,效果很好。任何想法可能是问题所在?

我写的这个算法与这个C# Perceptron 算法非常相似:


编辑:

这是一个较小训练集的示例:

#include <stdio.h>
#include <stdlib.h>
#include <math.h>

float randomFloat()
{
    float r = (float)rand() / (float)RAND_MAX;
    return r;
}

int calculateOutput(float weights[], float x, float y)
{
    float sum = x * weights[0] + y * weights[1];
    return (sum >= 0) ? 1 : -1;
}

int main(int argc, char *argv[])
{
    srand(time(NULL));

    // X coordinates of the training set.
    float x[] = { -3.2, 1.1, 2.7, -1 };

    // Y coordinates of the training set.
    float y[] = { 1.5, 3.3, 5.12, 2.1 };

    // The training set outputs.
    int outputs[] = { 1, -1, -1, 1 };

    int i = 0; // iterator

    FILE *fp;

    system("PAUSE");

    int patternCount = sizeof(x) / sizeof(int);

    float weights[2];
    weights[0] = randomFloat();
    weights[1] = randomFloat();

    float learningRate = 0.1;

    int iteration = 0;
    float globalError;

    do {
        globalError = 0;
        int p = 0; // iterator
        for (p = 0; p < patternCount; p++)
        {
            // Calculate output.
            int output = calculateOutput(weights, x[p], y[p]);

            // Calculate error.
            float localError = outputs[p] - output;

            if (localError != 0)
            {
                // Update weights.
                for (i = 0; i < 2; i++)
                {
                    float add = learningRate * localError;
                    if (i == 0)
                    {
                        add *= x[p];
                    }
                    else if (i == 1)
                    {
                        add *= y[p];
                    }
                    weights[i] +=  add;
                }
            }

            // Convert error to absolute value.
            globalError += fabs(localError);

            printf("Iteration %d Error %.2f\n", iteration, globalError);          
        }

        iteration++;

    } while (globalError != 0);

    // Display network generalisation.
    printf("X       Y     Output\n");
    float j, k;
    for (j = -1; j <= 1; j += .5)
    {
        for (j = -1; j <= 1; j += .5)
        {
            // Calculate output.
            int output = calculateOutput(weights, j, k);
            printf("%.2f  %.2f  %s\n", j, k, (output == 1) ? "Blue" : "Red");
        }
    }

    // Display modified weights.
    printf("Modified weights: %.2f %.2f\n", weights[0], weights[1]);

    system("PAUSE");
    return 0;
}
4

4 回答 4

172

在您当前的代码中,感知器成功地学习了决策边界的方向,但无法翻译它。

    年年
    ^ ^
    | - + \\ + | - \\ + +
    | - +\\ + + | - \\ + + +
    | - - \\ + | - - \\ +
    | - - + \\ + | - - \\ + +
    ---------------------> x --------------------> x
        像这样卡住需要像这样

(正如有人指出的,这是一个更准确的版本

问题在于您的感知器没有偏置项,即连接到值 1 的输入的第三个权重分量。

       w0 -----
    x ---->| |
           | f |----> 输出 (+1/-1)
    是---->| |
       w1 -----
               ^ w2
    1(偏差)---|

以下是我纠正问题的方法:

#include <stdio.h>
#include <stdlib.h>
#include <math.h>
#include <time.h>

#define LEARNING_RATE    0.1
#define MAX_ITERATION    100

float randomFloat()
{
    return (float)rand() / (float)RAND_MAX;
}

int calculateOutput(float weights[], float x, float y)
{
    float sum = x * weights[0] + y * weights[1] + weights[2];
    return (sum >= 0) ? 1 : -1;
}

int main(int argc, char *argv[])
{
    srand(time(NULL));

    float x[208], y[208], weights[3], localError, globalError;
    int outputs[208], patternCount, i, p, iteration, output;

    FILE *fp;
    if ((fp = fopen("test1.txt", "r")) == NULL) {
        printf("Cannot open file.\n");
        exit(1);
    }

    i = 0;
    while (fscanf(fp, "%f %f %d", &x[i], &y[i], &outputs[i]) != EOF) {
        if (outputs[i] == 0) {
            outputs[i] = -1;
        }
        i++;
    }
    patternCount = i;

    weights[0] = randomFloat();
    weights[1] = randomFloat();
    weights[2] = randomFloat();

    iteration = 0;
    do {
        iteration++;
        globalError = 0;
        for (p = 0; p < patternCount; p++) {
            output = calculateOutput(weights, x[p], y[p]);

            localError = outputs[p] - output;
            weights[0] += LEARNING_RATE * localError * x[p];
            weights[1] += LEARNING_RATE * localError * y[p];
            weights[2] += LEARNING_RATE * localError;

            globalError += (localError*localError);
        }

        /* Root Mean Squared Error */
        printf("Iteration %d : RMSE = %.4f\n",
            iteration, sqrt(globalError/patternCount));
    } while (globalError > 0 && iteration <= MAX_ITERATION);

    printf("\nDecision boundary (line) equation: %.2f*x + %.2f*y + %.2f = 0\n",
        weights[0], weights[1], weights[2]);

    return 0;
}

...具有以下输出:

Iteration 1 : RMSE = 0.7206
Iteration 2 : RMSE = 0.5189
Iteration 3 : RMSE = 0.4804
Iteration 4 : RMSE = 0.4804
Iteration 5 : RMSE = 0.3101
Iteration 6 : RMSE = 0.4160
Iteration 7 : RMSE = 0.4599
Iteration 8 : RMSE = 0.3922
Iteration 9 : RMSE = 0.0000

Decision boundary (line) equation: -2.37*x + -2.51*y + -7.55 = 0

这是上面使用 MATLAB 的代码的简短动画,显示了每次迭代的决策边界:

截屏

于 2009-11-11T09:22:23.710 回答
6

如果您将随机生成器的播种放在您 main 的开头而不是在每次调用时重新播种,这可能会有所帮助randomFloat,即

float randomFloat()
{
    float r = (float)rand() / (float)RAND_MAX;
    return r;
}

// ...

int main(int argc, char *argv[])
{
    srand(time(NULL));

    // X, Y coordinates of the training set.
    float x[208], y[208];
于 2009-11-08T17:30:52.887 回答
3

我在您的源代码中发现了一些小错误:

int patternCount = sizeof(x) / sizeof(int);

最好将其更改为

int patternCount = i;

所以你不必依赖你的 x 数组来获得正确的大小。

您在 p 循环内增加迭代,而原始 C# 代码在 p 循环外执行此操作。最好在 PAUSE 语句之前将 printf 和迭代++移到 p 循环之外 - 我也会删除 PAUSE 语句或将其更改为

if ((iteration % 25) == 0) system("PAUSE");

即使做了所有这些更改,您的程序仍然不会使用您的数据集终止,但输出更加一致,给出了一个在 56 到 60 之间波动的错误。

您可以尝试的最后一件事是在此数据集上测试原始 C# 程序,如果它也没有终止,则算法有问题(因为您的数据集看起来正确,请参阅我的可视化评论)。

于 2009-11-08T18:34:04.747 回答
0

globalError不会变为零,会如你所说的收敛到零,即它会变得非常小。

像这样改变你的循环:

int maxIterations = 1000000; //stop after one million iterations regardless
float maxError = 0.001; //one in thousand points in wrong class

do {
    //loop stuff here

    //convert to fractional error
    globalError = globalError/((float)patternCount);

} while ((globalError > maxError) && (i<maxIterations));

给出适用于您的问题的值maxIterationsmaxError

于 2009-11-09T16:19:55.563 回答