BP神经网络python代码

以下是一个简单的用Python实现的BP神经网络的代码示例：

import numpy as np
class NeuralNetwork:
    def __init__(self, layers):
        self.layers = layers
        self.num_layers = len(layers)
        self.weights = [np.random.randn(y, x) for x, y in zip(layers[:-1], layers[1:])]
        self.biases = [np.random.randn(y, 1) for y in layers[1:]]

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

    def sigmoid_derivative(self, z):
        return self.sigmoid(z) * (1 - self.sigmoid(z))

    def forward_propagation(self, a):
        for w, b in zip(self.weights, self.biases):
            a = self.sigmoid(np.dot(w, a) + b)
        return a

    def backward_propagation(self, x, y):
        activations = [x]
        zs = []
        activation = x
        for w, b in zip(self.weights, self.biases):
            z = np.dot(w, activation) + b
            zs.append(z)
            activation = self.sigmoid(z)
            activations.append(activation)

        delta = self.cost_derivative(activations[-1], y) * self.sigmoid_derivative(zs[-1])
        nabla_b[-1] = delta
        nabla_w[-1] = np.dot(delta, activations[-2].T)

        for l in range(2, self.num_layers):
            z = zs[-l]
            sp = self.sigmoid_derivative(z)
            delta = np.dot(self.weights[-l + 1].T, delta) * sp
            nabla_b[-l] = delta
            nabla_w[-l] = np.dot(delta, activations[-l - 1].T)

        return nabla_b, nabla_w

    def update_weights(self, mini_batch, learning_rate):
        nabla_b = [np.zeros(b.shape) for b in self.biases]
        nabla_w = [np.zeros(w.shape) for w in self.weights]
        for x, y in mini_batch:
            delta_nabla_b, delta_nabla_w = self.backward_propagation(x, y)
            nabla_b = [nb + dnb for nb, dnb in zip(nabla_b, delta_nabla_b)]
            nabla_w = [nw + dnw for nw, dnw in zip(nabla_w, delta_nabla_w)]
        self.weights = [w - (learning_rate / len(mini_batch)) * nw for w, nw in zip(self.weights, nabla_w)]
        self.biases = [b - (learning_rate / len(mini_batch)) * nb for b, nb in zip(self.biases, nabla_b)]

    def train(self, training_data, epochs, mini_batch_size, learning_rate):
        n = len(training_data)
        for epoch in range(epochs):
            np.random.shuffle(training_data)
            mini_batches = [training_data[k:k + mini_batch_size] for k in range(0, n, mini_batch_size)]
            for mini_batch in mini_batches:
                self.update_weights(mini_batch, learning_rate)

    def predict(self, x):
        return np.argmax(self.forward_propagation(x))

    def cost_derivative(self, output_activations, y):
        return output_activations - y

这个代码实现了一个具有一个输入层、一个或多个隐藏层和一个输出层的BP神经网络。你可以根据自己的需求进行修改和扩展。