softmax函数回归代码实现

以下是一个使用Python实现softmax函数回归的代码示例：

import numpy as np

def softmax(x):
    exp_x = np.exp(x)
    return exp_x / np.sum(exp_x)

def softmax_regression(X, y, num_classes, num_iterations, learning_rate):
    num_features = X.shape[1]
    weights = np.zeros((num_features, num_classes))

    for i in range(num_iterations):
        for j in range(X.shape[0]):
            x = X[j]
            y_true = y[j]
            y_pred = softmax(np.dot(x, weights))
            error = y_pred - (y_true == np.arange(num_classes))
            gradient = np.outer(x, error)
            weights -= learning_rate * gradient

    return weights

# Example usage
X = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
y = np.array([0, 1, 2])
num_classes = 3
num_iterations = 1000
learning_rate = 0.1

weights = softmax_regression(X, y, num_classes, num_iterations, learning_rate)
print(weights)

这个代码实现了一个简单的softmax函数回归模型，用于多分类问题。给定一个输入向量x，模型通过将x与权重矩阵相乘并应用softmax函数来预测每个类别的概率。在训练过程中，模型使用梯度下降算法来最小化交叉熵损失函数。