python实现BP神经网络代码

好的，以下是一个简单的Python BP神经网络实现的代码：

import numpy as np

class NeuralNetwork:
    
    def __init__(self, input_size, hidden_size, output_size):
        self.weights1 = np.random.randn(input_size, hidden_size)
        self.weights2 = np.random.randn(hidden_size, output_size)
        
    def sigmoid(self, x):
        return 1 / (1 + np.exp(-x))
    
    def sigmoid_derivative(self, x):
        return x * (1 - x)
    
    def feed_forward(self, X):
        self.hidden_layer = self.sigmoid(np.dot(X, self.weights1))
        self.output = self.sigmoid(np.dot(self.hidden_layer, self.weights2))
        return self.output
    
    def backpropagation(self, X, y, output):
        output_error = y - output
        output_delta = output_error * self.sigmoid_derivative(output)
        hidden_error = output_delta.dot(self.weights2.T)
        hidden_delta = hidden_error * self.sigmoid_derivative(self.hidden_layer)
        
        self.weights1 += X.T.dot(hidden_delta)
        self.weights2 += self.hidden_layer.T.dot(output_delta)
    
    def train(self, X, y):
        output = self.feed_forward(X)
        self.backpropagation(X, y, output)

X = np.array([[0,0,1], [0,1,1], [1,0,1], [1,1,1]])
y = np.array([[0,1,1,0]]).T

nn = NeuralNetwork(3, 5, 1)

for i in range(10000):
    nn.train(X, y)

print(nn.feed_forward(np.array([1,0,0])))

这是一个简单的三层神经网络，它可以学习XOR问题。我们使用sigmoid函数作为激活函数，并使用反向传播算法来更新权重。