期刊论文

Gao, Tao(gaotao_1989@126.com);Wang, Jian(wangjiannl@upc.edu.cn)

英文

Cognitive Systems Research

2214-4366

2021

68

62-72

10.1016/j.cogsys.2021.02.001

Scientific Research Fund of Hunan Provincial Education DepartmentHunan Provincial Education Department [19A063]; Science and Technology Innovation Program of Hunan Province [2016TP1020]; Hunan Provincial Key Laboratory of Intelligent Information Processing and Application; Double First-Class University Project of Hunan Province [Xiangjiaotong [2018] 469]; Application-oriented Characterized Disciplines; National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [61305075]; Natural Science Foundation of Shandong ProvinceNatural Science Foundation of Shandong Province [ZR2015AL014, ZR201709220208]; Fundamental Research Funds for the Central UniversitiesFundamental Research Funds for the Central Universities [15CX08011A, 18CX02036A]; Science and Technology Support Plan for Youth Innovation of University in Shandong Province [2019KJH002]; Major Scientific and Technological Projects of CNPC [ZD2019-183-008]

本校为第一机构

Elman recurrent network is a representative model with feedback mechanism. Although gradient descent method has been widely used to train Elman network, it frequently leads to slow convergence. According to optimization theory, conjugate gradient method is an alternative strategy in searching the descent direction during training. In this paper, an efficient conjugate gradient method has been presented to reach the optimal solution in two ways: (1) constructing a more effective conjugate coefficient, (2) determining adaptive learning rates in t...