感知器python实现

最新推荐文章于 2024-08-27 16:38:10 发布

qq_51086926

最新推荐文章于 2024-08-27 16:38:10 发布

阅读量228

点赞数

分类专栏： 1 文章标签： numpy python 机器学习

本文链接：https://blog.csdn.net/qq_51086926/article/details/127154659

版权

1 专栏收录该内容

9 篇文章 0 订阅

订阅专栏

import numpy as np

def func(x1, x2, y):
    global w0, w1, w2, n0, n1, n2
    a = 0.01
    w0, w1, w2 = 1, 1, 1
    n0, n1, n2 = 1, 1, 1
    for i in range(200):
        w0 = w0 - a * (summ(x1[i % 4], x2[i % 4]) - y[i % 4])
        w1 = w1 - a * (summ(x1[i % 4], x2[i % 4]) - y[i % 4]) * x1[i % 4]
        w2 = w2 - a * (summ(x1[i % 4], x2[i % 4]) - y[i % 4]) * x2[i % 4]
        n0 = (summ(x1[i % 4], x2[i % 4]) - y[i % 4])
        n1 = (summ(x1[i % 4], x2[i % 4]) - y[i % 4]) * x1[i % 4]
        n2 = (summ(x1[i % 4], x2[i % 4]) - y[i % 4]) * x2[i % 4]
        if (abs(n0) < 0.01 and abs(n1) < 0.01 and abs(n2) < 0.01):
            print(w0, w1, w2)
            print(n0, n1, n2)
            break
def summ(x1, x2):
    return w0 + w1 * x1 + w2 * x2
if __name__ == '__main__':
    x1 = np.array([0, 0, 1, 1])
    x2 = np.array([0, 1, 0, 1])
    y = np.array([0, 0, 0, 1])
    func(x1, x2, y)

运行结果：