感知器实现

邓冉

已于 2022-10-03 20:06:23 修改

阅读量94

点赞数

文章标签：机器学习 python 人工智能

于 2022-10-01 16:11:31 首次发布

本文链接：https://blog.csdn.net/qq_55321850/article/details/127058699

版权

import numpy as np


alpha = 0.01
theta0 = 0.5
theta1 = 0.5
theta2 = 1

x1 = np.array([0, 0, 1, 1])
x2 = np.array([0, 1, 0, 1])
y = np.array([0, 0, 0, 1])
y2 = np.array([0,1,1,1])
def mysum(x1,x2):
    return theta0+theta1*x1+theta2*x2


def activate(p,q):
    if (mysum(p,q)>0):
        return 1
    else:
        return 0

for i in range(1000):
    theta0 = theta0-alpha*(mysum(x1[i%4],x2[i%4]) - y[i%4])
    theta1 = theta1-alpha*(mysum(x1[i%4],x2[i%4])-y[i%4])*x1[i%4]
    theta2 = theta2-alpha*(mysum(x1[i%4],x2[i%4])-y[i%4])*x2[i%4]
    error0 = (mysum(x1[i%4],x2[i%4]) - y[i%4])
    error1 = (mysum(x1[i%4],x2[i%4]) - y[i%4])*x1[i%4]
    error2 = (mysum(x1[i%4],x2[i%4])-y[i%4])*x2[i%4]
    while (abs(error0)<0.01 and abs(error1)<0.01 and abs(error2)<0.01):

         print(error0,error1,error2)

实验结果：