ICode9
精准搜索请尝试： 精确搜索
首页
编程语言>
数据库
系统相关
互联网
其他分享
Python
Java
JavaScript
android
PHP
首页 > 编程语言> 文章详细

【人工智能导论：模型与算法】MOOC 8.3 误差后向传播(BP) 例题 编程验证

2022-04-19 19:04:27  阅读：171  来源： 互联网

标签：MOOC w8 8.3 w7 w6 w5 例题 round out


8.3 误差后向传播(BP)

原理和推导过程，参考慕课。
https://www.icourse163.org/course/ZJU-1003377027

输入值：x1, x2 = 0.5，0.3

输出值：y1, y2 =0.23， -0.07

激活函数：sigmoid

损失函数：MSE

初始权值：0.2 -0.4 0.5 0.6 0.1 -0.5 -0.3 0.8

目标：通过反向传播优化权值

 

反向传播1轮，检验PPT数值

=====正向计算：h1, h2, o1 ,o2=====0.56 0.5 0.48 0.53

=====损失函数：均方误差=====0.21

=====反向传播：误差传给每个权值=====0.01 0.01 0.01 0.01 0.03 0.08 0.03 0.07

=====更新前的权值=====0.2 -0.4 0.5 0.6 0.1 -0.5 -0.3 0.8

=====更新后的权值=====0.19 -0.41 0.49 0.59 0.07 -0.58 -0.33 0.73

import numpy as np


def sigmoid(z):
    a = 1 / (1 + np.exp(-z))
    return a


if __name__ == "__main__":
    w1 = 0.2
    w2 = -0.4
    w3 = 0.5
    w4 = 0.6
    w5 = 0.1
    w6 = -0.5
    w7 = -0.3
    w8 = 0.8

    x1 = 0.5
    x2 = 0.3

    y1 = 0.23
    y2 = -0.07

    print("=====输入值：x1, x2；真实输出值：y1, y2=====")
    print(x1, x2, y1, y2)

    in_h1 = w1 * x1 + w3 * x2
    out_h1 = sigmoid(in_h1)
    in_h2 = w2 * x1 + w4 * x2
    out_h2 = sigmoid(in_h2)

    in_o1 = w5 * out_h1 + w7 * out_h2
    out_o1 = sigmoid(in_o1)
    in_o2 = w6 * out_h1 + w8 * out_h2
    out_o2 = sigmoid(in_o2)

    print("=====正向计算：h1, h2, o1 ,o2=====")
    print(round(out_h1, 2), round(out_h2, 2), round(out_o1, 2), round(out_o2, 2))

    error = (1 / 2) * (out_o1 - y1)**2 + (1 / 2) * (out_o2 - y2)**2

    print("=====损失函数：均方误差=====")
    print(round(error, 2))

    # 反向传播
    d_o1 = out_o1 - y1
    d_o2 = out_o2 - y2
    # print(round(d_o1, 2), round(d_o2, 2))

    d_w5 = d_o1 * out_o1 * (1 - out_o1) * out_h1
    d_w7 = d_o1 * out_o1 * (1 - out_o1) * out_h2
    # print(round(d_w5, 2), round(d_w7, 2))
    d_w6 = d_o2 * out_o2 * (1 - out_o2) * out_h1
    d_w8 = d_o2 * out_o2 * (1 - out_o2) * out_h2
    # print(round(d_w6, 2), round(d_w8, 2))

    d_w1 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x1
    d_w3 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x2
    # print(round(d_w1, 2), round(d_w3, 2))

    d_w2 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x1
    d_w4 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x2
    # print(round(d_w2, 2), round(d_w4, 2))
    print("=====反向传播：误差传给每个权值=====")
    print(round(d_w1, 2), round(d_w2, 2), round(d_w3, 2), round(d_w4, 2), round(d_w5, 2), round(d_w6, 2), round(d_w7, 2),
          round(d_w8, 2))

    print("=====更新前的权值=====")
    print(round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
          round(w8, 2))

    w1 = w1 - d_w1
    w2 = w2 - d_w2
    w3 = w3 - d_w3
    w4 = w4 - d_w4
    w5 = w5 - d_w5
    w6 = w6 - d_w6
    w7 = w7 - d_w7
    w8 = w8 - d_w8

    print("=====更新后的权值=====")
    print(round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
          round(w8, 2))
View Code

 

增加到5轮，测试收敛

=====第6轮=====

正向计算：h1, h2, o1 ,o2

0.55 0.48 0.44 0.43

损失函数：均方误差

0.15

import numpy as np


def sigmoid(z):
    a = 1 / (1 + np.exp(-z))
    return a


def forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8):
    in_h1 = w1 * x1 + w3 * x2
    out_h1 = sigmoid(in_h1)
    in_h2 = w2 * x1 + w4 * x2
    out_h2 = sigmoid(in_h2)

    in_o1 = w5 * out_h1 + w7 * out_h2
    out_o1 = sigmoid(in_o1)
    in_o2 = w6 * out_h1 + w8 * out_h2
    out_o2 = sigmoid(in_o2)

    print("正向计算：h1, h2, o1 ,o2")
    print(round(out_h1, 2), round(out_h2, 2), round(out_o1, 2), round(out_o2, 2))

    error = (1 / 2) * (out_o1 - y1) ** 2 + (1 / 2) * (out_o2 - y2) ** 2

    print("损失函数：均方误差")
    print(round(error, 2))

    return out_o1, out_o2, out_h1, out_h2


def back_propagate(out_o1, out_o2, out_h1, out_h2):
    # 反向传播
    d_o1 = out_o1 - y1
    d_o2 = out_o2 - y2
    # print(round(d_o1, 2), round(d_o2, 2))

    d_w5 = d_o1 * out_o1 * (1 - out_o1) * out_h1
    d_w7 = d_o1 * out_o1 * (1 - out_o1) * out_h2
    # print(round(d_w5, 2), round(d_w7, 2))
    d_w6 = d_o2 * out_o2 * (1 - out_o2) * out_h1
    d_w8 = d_o2 * out_o2 * (1 - out_o2) * out_h2
    # print(round(d_w6, 2), round(d_w8, 2))

    d_w1 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x1
    d_w3 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x2
    # print(round(d_w1, 2), round(d_w3, 2))

    d_w2 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x1
    d_w4 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x2
    # print(round(d_w2, 2), round(d_w4, 2))
    print("反向传播：误差传给每个权值")
    print(round(d_w1, 2), round(d_w2, 2), round(d_w3, 2), round(d_w4, 2), round(d_w5, 2), round(d_w6, 2),
          round(d_w7, 2), round(d_w8, 2))

    return d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8


if __name__ == "__main__":
    w1 = 0.2
    w2 = -0.4
    w3 = 0.5
    w4 = 0.6
    w5 = 0.1
    w6 = -0.5
    w7 = -0.3
    w8 = 0.8
    x1 = 0.5
    x2 = 0.3
    y1 = 0.23
    y2 = -0.07
    print("=====输入值：x1, x2；真实输出值：y1, y2=====")
    print(x1, x2, y1, y2)
    print("=====更新前的权值=====")
    print(round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
          round(w8, 2))

    out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
    d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)

    # 步长
    step = 1

    w1 = w1 - step * d_w1
    w2 = w2 - step * d_w2
    w3 = w3 - step * d_w3
    w4 = w4 - step * d_w4
    w5 = w5 - step * d_w5
    w6 = w6 - step * d_w6
    w7 = w7 - step * d_w7
    w8 = w8 - step * d_w8

    print("第1轮更新后的权值")
    print(round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
          round(w8, 2))

    print("=====第2轮=====")
    out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
    d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)
    w1 = w1 - step * d_w1
    w2 = w2 - step * d_w2
    w3 = w3 - step * d_w3
    w4 = w4 - step * d_w4
    w5 = w5 - step * d_w5
    w6 = w6 - step * d_w6
    w7 = w7 - step * d_w7
    w8 = w8 - step * d_w8

    print("=====第3轮=====")
    out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
    d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)
    w1 = w1 - step * d_w1
    w2 = w2 - step * d_w2
    w3 = w3 - step * d_w3
    w4 = w4 - step * d_w4
    w5 = w5 - step * d_w5
    w6 = w6 - step * d_w6
    w7 = w7 - step * d_w7
    w8 = w8 - step * d_w8

    print("=====第4轮=====")
    out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
    d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)
    w1 = w1 - step * d_w1
    w2 = w2 - step * d_w2
    w3 = w3 - step * d_w3
    w4 = w4 - step * d_w4
    w5 = w5 - step * d_w5
    w6 = w6 - step * d_w6
    w7 = w7 - step * d_w7
    w8 = w8 - step * d_w8

    print("=====第5轮=====")
    out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
    d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)
    w1 = w1 - step * d_w1
    w2 = w2 - step * d_w2
    w3 = w3 - step * d_w3
    w4 = w4 - step * d_w4
    w5 = w5 - step * d_w5
    w6 = w6 - step * d_w6
    w7 = w7 - step * d_w7
    w8 = w8 - step * d_w8

    print("=====第6轮=====")
    out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
    print("更新后的权值")
    print(round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
          round(w8, 2))
View Code

 

改变步长（1变为50），看收敛速度

=====第6轮=====

正向计算：o1 ,o2

0.23 0.03

损失函数：均方误差

0.01

import numpy as np


def sigmoid(z):
    a = 1 / (1 + np.exp(-z))
    return a


def forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8):
    in_h1 = w1 * x1 + w3 * x2
    out_h1 = sigmoid(in_h1)
    in_h2 = w2 * x1 + w4 * x2
    out_h2 = sigmoid(in_h2)

    in_o1 = w5 * out_h1 + w7 * out_h2
    out_o1 = sigmoid(in_o1)
    in_o2 = w6 * out_h1 + w8 * out_h2
    out_o2 = sigmoid(in_o2)

    print("正向计算：o1 ,o2")
    print(round(out_o1, 2), round(out_o2, 2))

    error = (1 / 2) * (out_o1 - y1) ** 2 + (1 / 2) * (out_o2 - y2) ** 2

    print("损失函数：均方误差")
    print(round(error, 2))

    return out_o1, out_o2, out_h1, out_h2


def back_propagate(out_o1, out_o2, out_h1, out_h2):
    # 反向传播
    d_o1 = out_o1 - y1
    d_o2 = out_o2 - y2
    # print(round(d_o1, 2), round(d_o2, 2))

    d_w5 = d_o1 * out_o1 * (1 - out_o1) * out_h1
    d_w7 = d_o1 * out_o1 * (1 - out_o1) * out_h2
    # print(round(d_w5, 2), round(d_w7, 2))
    d_w6 = d_o2 * out_o2 * (1 - out_o2) * out_h1
    d_w8 = d_o2 * out_o2 * (1 - out_o2) * out_h2
    # print(round(d_w6, 2), round(d_w8, 2))

    d_w1 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x1
    d_w3 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x2
    # print(round(d_w1, 2), round(d_w3, 2))

    d_w2 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x1
    d_w4 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x2
    # print(round(d_w2, 2), round(d_w4, 2))
    print("反向传播：误差传给每个权值")
    print(round(d_w1, 2), round(d_w2, 2), round(d_w3, 2), round(d_w4, 2), round(d_w5, 2), round(d_w6, 2),
          round(d_w7, 2), round(d_w8, 2))

    return d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8


def update_w(w1, w2, w3, w4, w5, w6, w7, w8):
    # 步长
    step = 50
    w1 = w1 - step * d_w1
    w2 = w2 - step * d_w2
    w3 = w3 - step * d_w3
    w4 = w4 - step * d_w4
    w5 = w5 - step * d_w5
    w6 = w6 - step * d_w6
    w7 = w7 - step * d_w7
    w8 = w8 - step * d_w8
    return w1, w2, w3, w4, w5, w6, w7, w8


if __name__ == "__main__":
    w1 = 0.2
    w2 = -0.4
    w3 = 0.5
    w4 = 0.6
    w5 = 0.1
    w6 = -0.5
    w7 = -0.3
    w8 = 0.8
    x1 = 0.5
    x2 = 0.3
    y1 = 0.23
    y2 = -0.07
    print("=====输入值：x1, x2；真实输出值：y1, y2=====")
    print(x1, x2, y1, y2)
    print("=====更新前的权值=====")
    print(round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
          round(w8, 2))

    out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
    d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)
    w1, w2, w3, w4, w5, w6, w7, w8 = update_w(w1, w2, w3, w4, w5, w6, w7, w8)

    print("第1轮更新后的权值")
    print(round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
          round(w8, 2))

    print("=====第2轮=====")
    out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
    d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)
    w1, w2, w3, w4, w5, w6, w7, w8 = update_w(w1, w2, w3, w4, w5, w6, w7, w8)

    print("=====第3轮=====")
    out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
    d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)
    w1, w2, w3, w4, w5, w6, w7, w8 = update_w(w1, w2, w3, w4, w5, w6, w7, w8)

    print("=====第4轮=====")
    out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
    d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)
    w1, w2, w3, w4, w5, w6, w7, w8 = update_w(w1, w2, w3, w4, w5, w6, w7, w8)

    print("=====第5轮=====")
    out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
    d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)
    w1, w2, w3, w4, w5, w6, w7, w8 = update_w(w1, w2, w3, w4, w5, w6, w7, w8)

    print("=====第6轮=====")
    out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
    print("更新后的权值")
    print(round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
          round(w8, 2))
View Code

 

扩展到N轮，步长=5，训练N=1000次，查看效果

=====第999轮=====

正向计算：o1 ,o2

0.23038 0.00954

损失函数：均方误差

0.00316

 

import numpy as np


def sigmoid(z):
    a = 1 / (1 + np.exp(-z))
    return a


def forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8):
    in_h1 = w1 * x1 + w3 * x2
    out_h1 = sigmoid(in_h1)
    in_h2 = w2 * x1 + w4 * x2
    out_h2 = sigmoid(in_h2)

    in_o1 = w5 * out_h1 + w7 * out_h2
    out_o1 = sigmoid(in_o1)
    in_o2 = w6 * out_h1 + w8 * out_h2
    out_o2 = sigmoid(in_o2)

    print("正向计算：o1 ,o2")
    print(round(out_o1, 5), round(out_o2, 5))

    error = (1 / 2) * (out_o1 - y1) ** 2 + (1 / 2) * (out_o2 - y2) ** 2

    print("损失函数：均方误差")
    print(round(error, 5))

    return out_o1, out_o2, out_h1, out_h2


def back_propagate(out_o1, out_o2, out_h1, out_h2):
    # 反向传播
    d_o1 = out_o1 - y1
    d_o2 = out_o2 - y2
    # print(round(d_o1, 2), round(d_o2, 2))

    d_w5 = d_o1 * out_o1 * (1 - out_o1) * out_h1
    d_w7 = d_o1 * out_o1 * (1 - out_o1) * out_h2
    # print(round(d_w5, 2), round(d_w7, 2))
    d_w6 = d_o2 * out_o2 * (1 - out_o2) * out_h1
    d_w8 = d_o2 * out_o2 * (1 - out_o2) * out_h2
    # print(round(d_w6, 2), round(d_w8, 2))

    d_w1 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x1
    d_w3 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x2
    # print(round(d_w1, 2), round(d_w3, 2))

    d_w2 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x1
    d_w4 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x2
    # print(round(d_w2, 2), round(d_w4, 2))
    print("反向传播：误差传给每个权值")
    print(round(d_w1, 5), round(d_w2, 5), round(d_w3, 5), round(d_w4, 5), round(d_w5, 5), round(d_w6, 5),
          round(d_w7, 5), round(d_w8, 5))

    return d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8


def update_w(w1, w2, w3, w4, w5, w6, w7, w8):
    # 步长
    step = 5
    w1 = w1 - step * d_w1
    w2 = w2 - step * d_w2
    w3 = w3 - step * d_w3
    w4 = w4 - step * d_w4
    w5 = w5 - step * d_w5
    w6 = w6 - step * d_w6
    w7 = w7 - step * d_w7
    w8 = w8 - step * d_w8
    return w1, w2, w3, w4, w5, w6, w7, w8


if __name__ == "__main__":
    w1, w2, w3, w4, w5, w6, w7, w8 = 0.2, -0.4, 0.5, 0.6, 0.1, -0.5, -0.3, 0.8
    x1, x2 = 0.5, 0.3
    y1, y2 = 0.23, -0.07
    print("=====输入值：x1, x2；真实输出值：y1, y2=====")
    print(x1, x2, y1, y2)
    print("=====更新前的权值=====")
    print(round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
          round(w8, 2))

    for i in range(1000):
        print("=====第" + str(i) + "轮=====")
        out_o1, out_o2, out_h1, out_h2 = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
        d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)
        w1, w2, w3, w4, w5, w6, w7, w8 = update_w(w1, w2, w3, w4, w5, w6, w7, w8)

    print("更新后的权值")
    print(round(w1, 2), round(w2, 2), round(w3, 2), round(w4, 2), round(w5, 2), round(w6, 2), round(w7, 2),
          round(w8, 2))
View Code

 

修改输出值y2为正，收敛效果很好。

原因是：sigmoid，输出值应在（0,1）区间，所以最开始的假设 y2=-0.07，在这个模型里，无法很好的拟合。

 

优化后的源代码：

 

import numpy as np
import matplotlib.pyplot as plt


def sigmoid(z):
    a = 1 / (1 + np.exp(-z))
    return a


def forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8): # 正向传播
    in_h1 = w1 * x1 + w3 * x2
    out_h1 = sigmoid(in_h1)
    in_h2 = w2 * x1 + w4 * x2
    out_h2 = sigmoid(in_h2)

    in_o1 = w5 * out_h1 + w7 * out_h2
    out_o1 = sigmoid(in_o1)
    in_o2 = w6 * out_h1 + w8 * out_h2
    out_o2 = sigmoid(in_o2)

    error = (1 / 2) * (out_o1 - y1) ** 2 + (1 / 2) * (out_o2 - y2) ** 2

    return out_o1, out_o2, out_h1, out_h2, error


def back_propagate(out_o1, out_o2, out_h1, out_h2):    # 反向传播
    d_o1 = out_o1 - y1
    d_o2 = out_o2 - y2

    d_w5 = d_o1 * out_o1 * (1 - out_o1) * out_h1
    d_w7 = d_o1 * out_o1 * (1 - out_o1) * out_h2
    d_w6 = d_o2 * out_o2 * (1 - out_o2) * out_h1
    d_w8 = d_o2 * out_o2 * (1 - out_o2) * out_h2

    d_w1 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x1
    d_w3 = (d_w5 + d_w6) * out_h1 * (1 - out_h1) * x2
    d_w2 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x1
    d_w4 = (d_w7 + d_w8) * out_h2 * (1 - out_h2) * x2

    return d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8


def update_w(step,w1, w2, w3, w4, w5, w6, w7, w8):    #梯度下降，更新权值
    w1 = w1 - step * d_w1
    w2 = w2 - step * d_w2
    w3 = w3 - step * d_w3
    w4 = w4 - step * d_w4
    w5 = w5 - step * d_w5
    w6 = w6 - step * d_w6
    w7 = w7 - step * d_w7
    w8 = w8 - step * d_w8
    return w1, w2, w3, w4, w5, w6, w7, w8


if __name__ == "__main__":
    w1, w2, w3, w4, w5, w6, w7, w8 = 0.2, -0.4, 0.5, 0.6, 0.1, -0.5, -0.3, 0.8 # 可以给随机值，为配合PPT，给的指定值
    x1, x2 = 0.5, 0.3   # 输入值
    y1, y2 = 0.23, -0.07 # 正数可以准确收敛；负数不行。why? 因为用sigmoid输出，y1, y2 在 （0,1）范围内。
    N = 10             # 迭代次数
    step = 10           # 步长

    print("输入值：x1, x2；",x1, x2, "输出值：y1, y2:", y1, y2)
    eli = []
    lli = []
    for i in range(N):
        print("=====第" + str(i) + "轮=====")
        # 正向传播
        out_o1, out_o2, out_h1, out_h2, error = forward_propagate(x1, x2, y1, y2, w1, w2, w3, w4, w5, w6, w7, w8)
        print("正向传播:", round(out_o1, 5), round(out_o2, 5))
        print("损失函数：", round(error, 2))
        # 反向传播
        d_w1, d_w2, d_w3, d_w4, d_w5, d_w6, d_w7, d_w8 = back_propagate(out_o1, out_o2, out_h1, out_h2)
        # 梯度下降，更新权值
        w1, w2, w3, w4, w5, w6, w7, w8 = update_w(step,w1, w2, w3, w4, w5, w6, w7, w8)
        eli.append(i)
        lli.append(error)


    plt.plot(eli, lli)
    plt.ylabel('Loss')
    plt.xlabel('w')
    plt.show()

 

 

标签：MOOC,w8,8.3,w7,w6,w5,例题,round,out
来源： https://www.cnblogs.com/hbuwyg/p/16166814.html

本站声明： 1. iCode9 技术分享网（下文简称本站）提供的所有内容，仅供技术学习、探讨和分享；
2. 关于本站的所有留言、评论、转载及引用，纯属内容发起人的个人观点，与本站观点和立场无关；
3. 关于本站的所有言论和文字，纯属内容发起人的个人观点，与本站观点和立场无关；
4. 本站文章均是网友提供，不完全保证技术分享内容的完整性、准确性、时效性、风险性和版权归属；如您发现该文章侵犯了您的权益，可联系我们第一时间进行删除；
5. 本站为非盈利性的个人网站，所有内容不会用来进行牟利，也不会利用任何形式的广告来间接获益，纯粹是为了广大技术爱好者提供技术内容和技术思想的分享性交流网站。

关于我们 | 联系我们 | 留言反馈

专注分享技术，共同学习，共同进步。侵权联系[81616952@qq.com]

Copyright (C)ICode9.com, All Rights Reserved.

ICode9版权所有