神经网络模型代码python

以下是一个简单的神经网络模型代码的 Python 实现：

import numpy as np

class NeuralNetwork:
    def __init__(self, layers):
        self.layers = layers
        self.weights = [np.random.randn(layers[i], layers[i+1]) for i in range(len(layers)-1)]
        self.biases = [np.zeros((1, layers[i+1])) for i in range(len(layers)-1)]

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

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

    def feedforward(self, x):
        a = x
        for i in range(len(self.weights)):
            z = np.dot(a, self.weights[i]) + self.biases[i]
            a = self.sigmoid(z)
        return a

    def backpropagation(self, x, y):
        a = [x]
        z_list = []
        for i in range(len(self.weights)):
            z = np.dot(a[i], self.weights[i]) + self.biases[i]
            z_list.append(z)
            a.append(self.sigmoid(z))

        delta = (a[-1] - y) * self.sigmoid_derivative(a[-1])
        deltas = [delta]
        for i in range(len(self.weights)-1, 0, -1):
            delta = np.dot(deltas[-1], self.weights[i].T) * self.sigmoid_derivative(a[i])
            deltas.append(delta)
        deltas.reverse()

        for i in range(len(self.weights)):
            self.weights[i] -= 0.1 * np.dot(a[i].T, deltas[i])
            self.biases[i] -= 0.1 * deltas[i]

    def train(self, X, y, epochs):
        for epoch in range(epochs):
            for x, y_true in zip(X, y):
                self.backpropagation(x, y_true)

    def predict(self, X):
        return np.array([np.argmax(self.feedforward(x)) for x in X])

这个代码实现了一个基本的多层神经网络，使用了 sigmoid 激活函数和反向传播算法来训练模型。你可以传入一个层列表（例如 [2, 3, 1]）来定义神经网络的结构，然后使用 train 函数来训练模型，使用 predict 函数来进行预测。