Loading... ## sigmoid函数 激活函数:sigmoid表达式 $$ h(x) = \frac{1}{1 + exp(-x)} $$ e为纳皮尔常数2.71 ```python import matplotlib as mpl import matplotlib.pyplot as plt import numpy as np x = np.arange(-5.0,5.0,0.1) def sigmoid(x): return 1/(1+np.exp(-x)) y = sigmoid(x) plt.plot(x,y) plt.show() ``` sigmoid同阶跃函数相比较 sigmoid是一条平滑的曲线,对神经网络学习有着重要意义,且返回的是流动的实数信号 图像如图所示:  ## ReLU函数 $$ h(x)= \begin{cases} x (x>0) \\ 0 (x\le0) \end{cases} $$ ```python import matplotlib as mpl import matplotlib.pyplot as plt import numpy as np x = np.arange(-5.0,5.0,0.1) def relu(x): return np.maximum(0,x) y = relu(x) plt.plot(x,y) plt.show() ``` relu函数是一个非常简单的函数,maximum会选择较大的值进行输出 relu函数图像如图所示:  Last modification:December 5, 2020 © Allow specification reprint Support Appreciate the author AliPayWeChat Like 0 如果觉得我的内容对你有用,请随意赞赏