IDENTIFICATION USING FEEDFORWARD NETWORKS

被引：39

作者：

LEVIN, AU ^{[1
]}

NARENDRA, KS ^{[1
]}

机构：

[1] YALE UNIV,DEPT ELECT ENGN,CTR SYST SCI,NEW HAVEN,CT 06520

来源：

NEURAL COMPUTATION | 1995年 / 7卷 / 02期

关键词：

D O I：

10.1162/neco.1995.7.2.349

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper is concerned with the identification of an unknown nonlinear dynamic system when only the inputs and outputs are accessible for measurement. Specifically we investigate the use of feedforward neural networks as models for the input-output behavior of such systems. Relying on the approximation capabilities of feedforward neural networks and under mild assumptions regarding the properties of the underlying nonlinear system, it is shown that there exists a feedforward network that for almost all inputs (an open and dense set) will display the input-output behavior of the system.

引用

页码：349 / 357

页数：9

共 50 条

[31] On using feedforward neural networks for clinical diagnostic tasks
Dorffner, G.
Porenta, G.
[J]. Artificial Intelligence in Medicine, 1994, 6 (05) : 417 - 435
[32] Minimal feedforward parity networks using threshold gates
Fung, HK
Li, LK
[J]. NEURAL COMPUTATION, 2001, 13 (02) : 319 - 326
[33] Recognition of Isolated Words Using Feedforward Neural Networks
Kacur, Juraj
Urbancikova, Lucia
[J]. 2018 25TH INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING (IWSSIP), 2018,
[34] Input-output model identification of small and large induction motors using multilayer feedforward neural networks
Jang, SS
AhmedZaid, S
Taylor, CW
Sobajic, DJ
[J]. 1997 IEEE INTERNATIONAL ELECTRIC MACHINES AND DRIVES CONFERENCE RECORD, 1997, : MD141 - MD143
[35] Feedforward concept networks
Slezak, D
Szczuka, M
Wrólewski, J
[J]. MONITORING, SECURITY, AND RESCUE TECHNIQUES IN MULTIAGENT SYSTEMS, 2005, : 281 - 292
[36] Holomorphic feedforward networks
Douglas, Michael R.
[J]. PURE AND APPLIED MATHEMATICS QUARTERLY, 2022, 18 (01) : 251 - 268
[37] FEEDFORWARD NETWORKS - A TUTORIAL
COHEN, D
SHAWETAYLOR, J
[J]. NEW DEVELOPMENTS IN NEURAL COMPUTING, 1989, : 1 - 13
[38] Optimized feedforward neural networks. for on-line identification of nonlinear models
Alessandri, A
Sanguineti, M
Maggiore, M
[J]. PROCEEDINGS OF THE 41ST IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-4, 2002, : 1751 - 1756
[39] Application of multilayer feedforward networks to the parameter identification of non-uniform media
Gong, Pu
Lu, Lijun
Wang, Donghua
[J]. Huazhong Ligong Daxue Xuebao/Journal Huazhong (Central China) University of Science and Technology, 1998, 26 (10): : 19 - 21
[40] Identification of chaotic systems with large noise based on regularized feedforward neural networks
Li, DM
[J]. Proceedings of 2005 International Conference on Machine Learning and Cybernetics, Vols 1-9, 2005, : 4060 - 4063

← 1 2 3 4 5 →