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

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 CUTERtest functions as well as on a neural network. They show that the proposed method has promising performance from a computational perspective.

کلیدواژه ها:

Nonlinear programming ، unconstrained optimization ، Three term conjugate gradient method ، Neural Network