In particular, when the number of neurons in hidden layer equals the number of training patterns, the global minima with zero cost functions are obtained.

 
  • 一個(gè)特例是當隱層神經(jīng)元的個(gè)數與樣本個(gè)數相等時(shí),就可以求得代價(jià)函數值為0的全局最小點(diǎn)。
今日熱詞
目錄 附錄 查詞歷史
国内精品美女A∨在线播放xuan