Publikationen
Digital
AdaFamily: A family of Adam-like adaptive gradient methods
Beteiligte Autoren der JOANNEUM RESEARCH:
Autor*innen:
Fassold, Hannes
Abstract:
We propose AdaFamily, a novel method for training deep neural networks. It is a family of adaptive gradient methods and can be interpreted as sort of a blend of the optimization algorithms Adam, AdaBelief and AdaMomentum. We perform experiments on standard datasets for image classification, demonstrating that our proposed method outperforms these algorithms.
Titel:
AdaFamily: A family of Adam-like adaptive gradient methods
Herausgeber (Verlag):
arXiv
Publikationsdatum
2022
Copyright
Creative Commons Attribution 4.0 International
Publikationsreihe
Herausgeber(Verlag)
arXiv
