It learns the weighting value based on the difference between the ideal output and the actual output, and then modifies the weighting value via back propagation.

 
  • 而當學(xué)習權值時(shí),卻是根據理想輸出與實(shí)際的誤差,由前向后逐層修改權值(Back Propagation)。
今日熱詞
目錄 附錄 查詞歷史
国内精品美女A∨在线播放xuan