BP神经网络分类算法代码

以下是一个简单的基于BP神经网络的分类算法的Python代码示例：

import numpy as np

# 定义sigmoid激活函数
def sigmoid(x):
    return 1.0 / (1.0 + np.exp(-x))

# 定义BP神经网络分类器类
class BPNNClassifier(object):
    def __init__(self, input_size, hidden_size, output_size, learning_rate=0.1):
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.output_size = output_size
        self.learning_rate = learning_rate
        
        # 初始化权重
        self.weights1 = np.random.randn(self.input_size, self.hidden_size)
        self.bias1 = np.random.randn(self.hidden_size)
        self.weights2 = np.random.randn(self.hidden_size, self.output_size)
        self.bias2 = np.random.randn(self.output_size)

    # 前向传播
    def forward(self, X):
        self.layer1 = sigmoid(np.dot(X, self.weights1) + self.bias1)
        self.layer2 = sigmoid(np.dot(self.layer1, self.weights2) + self.bias2)
        return self.layer2

    # 反向传播
    def backward(self, X, y, output):
        output_error = y - output
        output_delta = output_error * sigmoid(output) * (1 - sigmoid(output))

        layer1_error = np.dot(output_delta, self.weights2.T)
        layer1_delta = layer1_error * sigmoid(self.layer1) * (1 - sigmoid(self.layer1))

        # 更新权重和偏置
        self.weights2 += self.learning_rate * np.dot(self.layer1.T, output_delta)
        self.bias2 += self.learning_rate * np.sum(output_delta, axis=0)
        self.weights1 += self.learning_rate * np.dot(X.T, layer1_delta)
        self.bias1 += self.learning_rate * np.sum(layer1_delta, axis=0)

    # 拟合数据
    def fit(self, X, y, epochs=200):
        for i in range(epochs):
            output = self.forward(X)
            self.backward(X, y, output)

    # 预测新数据
    def predict(self, X):
        return np.argmax(self.forward(X), axis=1)

使用示例：

# 导入数据
from sklearn.datasets import load_iris
iris = load_iris()
X = iris.data
y = iris.target

# 实例化分类器
clf = BPNNClassifier(input_size=X.shape[1], hidden_size=10, output_size=len(np.unique(y)))

# 拟合数据
clf.fit(X, y, epochs=500)

# 预测新数据
new_X = np.array([[5.1, 3.5, 1.4, 0.2],
                  [6.2, 3.4, 5.4, 2.3],
                  [4.9, 3.0, 1.4, 0.2]])
print(clf.predict(new_X))