مجله مدل‌سازی پیشرفته ریاضی

مجله مدل‌سازی پیشرفته ریاضی

A NEW THREE-TERM CONJUGATE GRADIENT METHOD AND ITS APPLICATION IN TRAINING NEURAL NETWORK

نوع مقاله : مقاله پژوهشی

نویسندگان
1 Department of Mathematics, Faculty of Mathematical Sciences and Computer, Semnan University,
2 Faculty of Mathematics, Statistics and Computer Science, Semnan University, Semnan, Iran
چکیده
Jiang et al. introduced a new family of three-term conjugate gradient tech niques that were theoretically effective and numerically ecient. Here, based on their study, we propose a new three-term conjugate gradient algorithm as a modi fied version of the Hastens-Stifel method. Numerical experiments are performed on a set of CUTER
test functions as well as on a neural network. They show that the proposed method has promising performance from a computational perspective.
کلیدواژه‌ها
موضوعات

  • تاریخ دریافت 25 آذر 1403
  • تاریخ بازنگری 08 مهر 1404
  • تاریخ پذیرش 19 خرداد 1405