用scipy.minimize()训练逻辑神经元

import numpy as np
from scipy.optimize import minimize

# 定义成本函数
def cost_function(theta, X, y):
    m = len(y)
    h = sigmoid(np.dot(X, theta))
    J = (-1/m) * np.sum(y*np.log(h) + (1-y)*np.log(1-h))
    return J

# 定义激活函数
def sigmoid(z):
    return 1 / (1 + np.exp(-z))

# 训练逻辑神经元
def train_logic_neuron(X, y):
    # 初始化权重
    initial_theta = np.zeros(X.shape[1])
    
    # 最小化成本函数
    result = minimize(cost_function, initial_theta, args=(X, y), method='BFGS', options={'maxiter': 400})
    
    # 获取训练后的权重
    trained_theta = result.x
    
    return trained_theta

# 示例数据
X = np.array([[1, 2], [3, 4], [5, 6]])
y = np.array([0, 1, 0])

# 训练逻辑神经元
trained_theta = train_logic_neuron(X, y)

print("训练后的权重：", trained_theta)