Home // eKNOW 2020, The Twelfth International Conference on Information, Process, and Knowledge Management // View article

Acceleration Technique of Two-Phase Quasi-Newton Method with Momentum for Optimization Problems

Authors:
Sudeera Hasaranga Gunathilaka Mastiyage Don
Shahrzad Mahboubi
Hiroshi Ninomiya

Keywords: neural networks; training algorithm; Two-Phase Quasi-Newton method; Nesterov’s accelerated gradient; momentum terms.

Abstract:
This paper describes a novel acceleration technique of the Two-Phase Quasi-Newton method using momentum terms for optimization problems. The performance of the proposed algorithm is evaluated on an unconstrained optimization problem in neural network training. The results show that the proposed algorithm has a much faster convergence than the conventional Two-Phase Quasi-Newton method.

Pages: 59 to 61

Copyright: Copyright (c) IARIA, 2020

Publication date: March 22, 2020

Published in: conference

ISSN: 2308-4375

ISBN: 978-1-61208-765-8

Location: Valencia, Spain

Dates: from November 21, 2020 to November 25, 2020