Optimising neural network training efficiency through spectral parameter-based multiple adaptive learning rates

The process of training neural networks heavily involves solving optimization problems. Most optimization algorithms use a !xed learning rate or a simpli!ed adaptive updating scheme in every iteration. In this paper, we propose a stochastic gradient descent method with multiple adaptive learning...

Full description

Bibliographic Details

Main Authors:	Yeong, Lin Koay, Hong, Seng Sim, Yong, Kheng Goh, Sing, Yee Chua, Wah, June Leong
Format:	Conference or Workshop Item
Language:	en
Published:	Association for Computing Machinery 2024
Online Access:	http://psasir.upm.edu.my/id/eprint/121559/1/121559.pdf http://psasir.upm.edu.my/id/eprint/121559/ https://dl.acm.org/doi/proceedings/10.1145/3708778
Tags:	Add Tag No Tags, Be the first to tag this record!