Jensen–Shannon divergence

 JensenShannon divergence(J-S散度) is a method of measuring the similarity between two probability distributions.

It is based on the Kullback–Leibler divergence(K-L散度), with some notable

(and useful) differences, including that it is symmetric and it is always a finite value.

The Jensen–Shannon divergence (JSD) M_{+}^{1}(A)\times M_{+}^{1}(A)\rightarrow [0,\infty {}) is a symmetrized and smoothed version of the Kullback–Leibler divergence D(P\parallel Q). It is defined by:

{​{\rm {JSD}}}(P\parallel Q)={\frac  {1}{2}}D(P\parallel M)+{\frac  {1}{2}}D(Q\parallel M)   where   M={\frac  {1}{2}}(P+Q)

The Jensen–Shannon divergence is bounded by 1 for two probability distributions, given that one uses the base 2 logarithm.    0\leq {​{\rm {JSD}}}(P\parallel Q)\leq 1

For log base e, or ln, which is commonly used in statistical thermodynamics, the upper bound is ln(2):    0\leq {​{\rm {JSD}}}(P\parallel Q)\leq \ln(2)

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值