Python-sklearn-ActivationFunction

最新推荐文章于 2024-08-14 17:18:35 发布

2401_82889064

最新推荐文章于 2024-08-14 17:18:35 发布

阅读量324

点赞数 9

分类专栏：机器学习文章标签： python sklearn

本文链接：https://blog.csdn.net/2401_82889064/article/details/136401276

版权

机器学习专栏收录该内容

14 篇文章 0 订阅

订阅专栏

"""
@Title: activation_function
@Time: 2024/3/1
@Author: Michael Jie
"""

import numpy as np


# Sigmoid
def sigmoid(x):
    return 1 / (1 + np.exp(-x))


# Tanh
def tanh(x):
    return (np.exp(x) - np.exp(-x)) / (np.exp(x) + np.exp(-x))


# ReLU
def relu(x):
    return np.maximum(0, x)


# Leaky ReLU
def leaky_relu(x, alpha=0.01):
    return np.maximum(alpha * x, x)


# ELU
def elu(x, alpha=0.01):
    return np.maximum(alpha * (np.exp(x) - 1), x)


# Softmax
def softmax(x):
    return np.exp(x) / np.sum(np.exp(x))


if __name__ == '__main__':
    print(sigmoid(np.array([0, -1, 1, -99, 99])))
    print(tanh(np.array([0, -1, 1, -99, 99])))
    print(relu(np.array([0, -1, 1, -99, 99])))
    print(leaky_relu(np.array([0, -1, 1, -99, 99])))
    print(elu(np.array([0, -1, 1, -99, 99])))
    print(softmax(np.array([0, -1, 1, -99, 99])))