BP神经网络PYTHON代码

BP神经网络是一种常用的人工神经网络，可用于分类、回归、模式识别等问题。下面是一个简单的BP神经网络的Python实现代码：

import numpy as np

class BPNN:
    def __init__(self, input_size, hidden_size, output_size, learning_rate):
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.learning_rate = learning_rate
        
        self.w1 = np.random.rand(self.input_size, self.hidden_size)
        self.b1 = np.random.rand(self.hidden_size)
        self.w2 = np.random.rand(self.hidden_size, self.output_size)
        self.b2 = np.random.rand(self.output_size)

    def sigmoid(self, x):
        return 1 / (1 + np.exp(-x))

    def sigmoid_derivative(self, x):
        return x * (1 - x)

    def forward(self, x):
        self.z1 = np.dot(x, self.w1) + self.b1
        self.a1 = self.sigmoid(self.z1)
        self.z2 = np.dot(self.a1, self.w2) + self.b2
        self.a2 = self.sigmoid(self.z2)
        return self.a2

    def backward(self, x, y, output):
        delta2 = (y - output) * self.sigmoid_derivative(output)
        d_w2 = np.dot(self.a1.T, delta2)
        delta1 = np.dot(delta2, self.w2.T) * self.sigmoid_derivative(self.a1)
        d_w1 = np.dot(x.T, delta1)

        self.w1 += self.learning_rate * d_w1
        self.b1 += self.learning_rate * np.sum(delta1, axis=0)
        self.w2 += self.learning_rate * d_w2
        self.b2 += self.learning_rate * np.sum(delta2, axis=0)

    def train(self, x, y):
        output = self.forward(x)
        self.backward(x, y, output)

# 示例
X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
Y = np.array([, , , ])

bpnn = BPNN(2, 4, 1, 0.5)
for i in range(10000):
    for j in range(4):
        bpnn.train(X[j], Y[j])

print(bpnn.forward(np.array([0, 0])))
print(bpnn.forward(np.array([0, 1])))
print(bpnn.forward(np.array([1, 0])))
print(bpnn.forward(np.array([1, 1])))

以上代码实现了一个简单的BP神经网络，其中`__init__`方法初始化了神经网络的权重和偏置，`sigmoid`方法实现了sigmoid激活函数，`forward`方法实现了前向传播过程，`backward`方法实现了反向传播过程，`train`方法实现了训练过程。在示例中，我们使用BP神经网络实现了异或逻辑运算。