シグモイドとソフトマックスの関係
from x/(x+1)
シグモイドとソフトマックスの関係
\sigma(s) = 1 / (1 + \exp(-s))
m(x_i) = \exp(x_i) / \sum \exp(x_i)
\sigma(s) = \exp(s) / (\exp(s) + \exp(s)\exp(-s)) = \exp(s) / (\exp(s) + 1) = \exp(s) / (\exp(s) + \exp(0))
つまりシグモイドは2要素のソフトマックスであって、注目している事象の余事象の出力が0の場合に相当する
"Engineer's way of creating knowledge" the English version of my book is now available on [Engineer's way of creating knowledge]
(C)NISHIO Hirokazu / Converted from [Scrapbox] at [Edit]