c - 感知器学习算法不收敛到 0

Question

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:Data Set

我已经删除了所有不相关的代码。基本上它现在所做的是读取 test1.txt 文件并将值从它加载到三个数组:x、y、outputs.

然后有一个perceptron learning algorithm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(例如 5 个点)时，效果很好。有什么想法可能是问题所在吗？

我写的这个算法和这个很相似C# Perceptron algorithm :

---

编辑:

这是一个训练集较小的例子:

#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;
}

Answer 1

在您当前的代码中，perceptron成功学习了决策边界的方向，但无法翻译它。

    y                              y    ^                              ^    |  - + \\  +                   |  - \\ +   +    | -    +\\ +   +               | -   \\  + +   +    | - -    \\ +                  | - -  \\    +    | -  -  + \\  +                | -  -  \\ +   +    ---------------------> x       --------------------> x        stuck like this            need to get like this

^{(as someone pointed out, here is a more accurate version)}

The problem lies in the fact that your perceptron has no bias term, i.e. a third weight component connected to an input of value 1.

       w0   -----    x ---->|     |           |  f  |----> output (+1/-1)    y ---->|     |       w1   -----               ^ w2    1(bias) ---|

The following is how I corrected the problem:

#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;
}

... 输出如下:

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

下面是使用 MATLAB 的上述代码的简短动画，显示了 decision boundary在每次迭代中: