Why is the learning rate for the bias usually twice as large as the the LR for the weights?

조회 수: 3 (최근 30일)
Salma Hassan
Salma Hassan 2018년 1월 3일
편집: Image Analyst 2018년 1월 5일
Why is the learning rate for the bias usually twice as large as the the LR for the weights?
  댓글 수: 2
Salma Hassan
Salma Hassan 2018년 1월 5일
편집: Image Analyst 2018년 1월 5일
https://datascience.stackexchange.com/questions/23549/why-is-the-learning-rate-for-the-bias-usually-twice-as-large-as-the-the-lr-for-t
on the other hand if you check, for example alexnet layers you will find that net.Layers(N, 1).BiasLearnRateFactor=2 and net.Layers(N, 1).WeightLearnRateFactor = 1

댓글을 달려면 로그인하십시오.

이 질문에 답변하려면 로그인하십시오.

답변 (0개)

카테고리

Help Center 및 File Exchange에서 Image Data Workflows에 대해 자세히 알아보기

태그

제품

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by