1.Logistic函数
在维基百科中,对logistic函数这样介绍道:
A logistic function or logistic curve is a common "S" shape (sigmoid curve), with equation: $$f(x)=\frac{L}{1+e^{-k(x-x0)}}$$
Logistic函数呈'S'型曲线,当x趋于-∞时函数趋于0,当x趋于+∞时函数趋于L。
2.Softmax函数
softmax函数定义如下:
In mathematics, the softmax function, or normalized exponential function,is a generalization of the logistic function that "squashes" a K-dimensional vector $\mathbf{Z}$ of arbitrary real values to a K-dimensional vector $\sigma(\textbf{Z})$ of real values in the range (0, 1) that add up to 1. The function is given by
$$\sigma(\textbf{Z})_j=\frac{e^Z_j}{\sum_{k=1}^{K}e^{Z_k}}\quad j=1,2,...,K$$
在数学定义中,Softmax函数是对Logistic函数的一般化。它的作用是将一个K维实数向量的各分量值映射到(0,1),且各分量值之和为1。
3.对比
从定义中不难看出,Softmax函数是对Logistic函数的延伸扩展。拿Sigmoid函数(Logistic函数的一种)为例,它将单个变量的取值变换到(0,1),而Softmax函数是Sigmoid函数的多维形式,参数不是单个变量而是多维向量。由于维度不同,Logistic函数常被应用于回归问题(称为Logistic回归)和神经网络的激活函数。而Softmax函数常被用于神经网络的最后一层,进行多分类。
4.参考资料
更详细的介绍参考:http://www.cnblogs.com/maybe2030/p/5678387.html?utm_source=tuicool&utm_medium=referral
z {\displaystyle \mathbf {z} } of arbitrary real values to a K-dimensional vector σ ( z ) {\displaystyle \sigma (\mathbf {z} )} of real values in the range (0, 1) that add up to 1. The function is given by
- σ ( z ) j = e z j ∑ k = 1 K e z k {\displaystyle \sigma (\mathbf {z} )_{j}={\frac {e^{z_{j}}}{\sum _{k=1}^{K}e^{z_{k}}}}} for j = 1, …, K.