使用numpy实现简单的误差逆传播算法模型

谁践踏了优雅 2024-03-30 17:13 71阅读 0赞

# -*- coding: utf-8 -*-
    import numpy as np
    
    # 定义激活函数
    def sigmoid(x):
        return 1/(1+np.exp(-x))
    
    # 定义激活函数的导数
    def sigmoid_derivative(x):
        return x*(1-x)
    
    # 输入数据
    input_data = np.array([[0,0,1],
                           [0,1,1],
                           [1,0,1],
                           [1,1,1]])
    
    # 期望输出
    expected_output = np.array([[0,0,1,1]]).T
    
    # 随机初始化权重
    np.random.seed(1)
    weight_0_1 = 2*np.random.random((3,256)) - 1
    weight_1_2 = 2*np.random.random((256,256)) - 1
    weight_2_3 = 2*np.random.random((256,10)) - 1
    
    # 设置学习率
    learning_rate = 0.1
    
    # 开始训练
    for j in range(10000):
        # 正向传播
        layer_0 = input_data
        layer_1 = sigmoid(np.dot(layer_0,weight_0_1))
        layer_2 = sigmoid(np.dot(layer_1,weight_1_2))
        layer_3 = sigmoid(np.dot(layer_2,weight_2_3))
    
        # 计算误差
        layer_3_error = expected_output - layer_3
    
        # 反向传播
        layer_3_delta = layer_3_error * sigmoid_derivative(layer_3)
        layer_2_error = layer_3_delta.dot(weight_2_3.T)
        layer_2_delta = layer_2_error * sigmoid_derivative(layer_2)
        layer_1_error = layer_2_delta.dot(weight_1_2.T)
        layer_1_delta = layer_1_error * sigmoid_derivative(layer_1)
    
        # 更新权重
        weight_2_3 += layer_2.T.dot(layer_3_delta)*learning_rate
        weight_1_2 += layer_1.T.dot(layer_2_delta)*learning_rate
        weight_0_1 += layer_0.T.dot(layer_1_delta)*learning_rate
    
    # 输出最终预测结果
    print(layer_3)