感知器训练

import numpy as np

class Perceptron:
    def __init__(self, input_dim, learning_rate=0.01):
        # 初始化权重和偏置
        self.weights = np.random.randn(input_dim)
        self.bias = np.random.randn()
        self.learning_rate = learning_rate

    def step_function(self, z):
        # 阶跃函数
        return 1 if z >= 0 else 0

    def predict(self, x):
        # 计算线性组合
        z = np.dot(self.weights, x) + self.bias
        # 使用阶跃函数进行预测
        return self.step_function(z)

    def train(self, X, y, epochs=100):
        for epoch in range(epochs):
            for i in range(len(X)):
                # 前向传播
                prediction = self.predict(X[i])
                # 计算误差
                error = y[i] - prediction
                # 更新权重和偏置
                self.weights += self.learning_rate * error * X[i]
                self.bias += self.learning_rate * error

# 示例数据
X = np.array([[0, 0], [0, 1], [1, 0], [1, 1]])
y = np.array([0, 0, 0, 1])  # AND逻辑门

# 创建感知器
input_dim = X.shape[1]
perceptron = Perceptron(input_dim)

# 训练感知器
perceptron.train(X, y, epochs=10)

# 测试感知器
for x in X:
    print(f"Input: {x}, Predicted: {perceptron.predict(x)}")