A nonmonotone learning rate strategy for SGD training of deep neural networks - researchr publication

researchr

You are not signed in
Sign in
Sign up

Nitish Shirish Keskar, George Saon. A nonmonotone learning rate strategy for SGD training of deep neural networks. In 2015 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2015, South Brisbane, Queensland, Australia, April 19-24, 2015. pages 4974-4978, IEEE, 2015. [doi]

Abstract is missing.

runs on WebDSL