bp神经网络回归代码训练模型

好的，以下是一个简单的BP神经网络回归代码训练模型的示例：

import numpy as np

class BPNeuralNetwork:
    def __init__(self, input_dim, hidden_dim, output_dim, lr=0.1):
        self.input_dim = input_dim
        self.hidden_dim = hidden_dim
        self.output_dim = output_dim
        self.lr = lr

        self.weights1 = np.random.randn(input_dim, hidden_dim)
        self.bias1 = np.random.randn(hidden_dim)

        self.weights2 = np.random.randn(hidden_dim, output_dim)
        self.bias2 = np.random.randn(output_dim)

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

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

    def forward(self, x):
        self.layer1 = self.sigmoid(np.dot(x, self.weights1) + self.bias1)
        self.output = np.dot(self.layer1, self.weights2) + self.bias2
        return self.output

    def backward(self, x, y, output):
        error = y - output
        output_delta = error
        layer1_error = output_delta.dot(self.weights2.T)
        layer1_delta = layer1_error * self.sigmoid_derivative(self.layer1)

        self.weights2 += self.lr * self.layer1.reshape(self.hidden_dim, 1).dot(output_delta.reshape(1, self.output_dim))
        self.bias2 += self.lr * output_delta

        self.weights1 += self.lr * x.reshape(self.input_dim, 1).dot(layer1_delta.reshape(1, self.hidden_dim))
        self.bias1 += self.lr * layer1_delta

    def train(self, x, y, epochs):
        for i in range(epochs):
            output = self.forward(x)
            self.backward(x, y, output)

    def predict(self, x):
        return self.forward(x)

使用方法：

# 构造数据
X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
y = np.array([[0], [1], [1], [0]])

# 定义网络
model = BPNeuralNetwork(2, 4, 1)

# 训练网络
model.train(X, y, 10000)

# 预测结果
print(model.predict(X))

这个示例中，我们构造了一个2-4-1的BP神经网络，使用四个样本进行训练，并最终进行预测。您可以根据自己的需求调整网络的输入、隐藏和输出节点数，以及学习率和训练次数。