Why is the Neural Network training slow when I don't use the Matlab Toolbox?

조회 수: 1 (최근 30일)
David Franco
David Franco 2020년 12월 28일
I am trying to optimize neural weights using the standalone Levenberg-Marquard algorithm, but the ANN training is much slower than when using the same algorithm in the Toolbox (trainlm). What causes this?
Standalone Levenberg-Marquard = 30 minutes
trainlm = 5 seconds
Same final accuracy...

이 질문에 답변하려면 로그인하십시오.

답변 (0개)

카테고리

Help Center 및 File Exchange에서 Define Shallow Neural Network Architectures에 대해 자세히 알아보기

태그

제품


릴리스

R2018b

Community Treasure Hunt

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

Start Hunting!

Translated by