A learning result for continuous-time recurrent neural networks

被引：12

作者：

Sontag, ED ^{[1
]}

机构：

[1] Rutgers State Univ, Dept Math, Hill Ctr, Piscataway, NJ 08854 USA

来源：

SYSTEMS & CONTROL LETTERS | 1998年 / 34卷 / 03期

关键词：

recurrent neural networks; system identification; computational learning theory;

D O I：

10.1016/S0167-6911(98)00006-1

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The following learning problem is considered, for continuous-time recurrent neural networks having sigmoidal activation functions. Given a "black box" representing an unknown system, measurements of output derivatives are collected, for a set of randomly generated inputs, and a network is used to approximate the observed behavior. It is shown that the number of inputs needed for reliable generalization (the sample complexity of the learning problem) is upper bounded by an expression that grows polynomially with the dimension of the network and logarithmically with the number of output derivatives being matched. (C) 1998 Elsevier Science B.V. All rights reserved.

引用

页码：151 / 158

页数：8

共 50 条

[21] A Comprehensive Review of Stability Analysis of Continuous-Time Recurrent Neural Networks
Zhang, Huaguang
Wang, Zhanshan
Liu, Derong
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2014, 25 (07) : 1229 - 1262
[22] Stability Analysis of a General Class of Continuous-Time Recurrent Neural Networks
Fu, Chaojin
Wang, Zhongsheng
ADVANCES IN NEURAL NETWORKS - ISNN 2009, PT 1, PROCEEDINGS, 2009, 5551 : 340 - +
[23] APPROXIMATION OF DYNAMICAL-SYSTEMS BY CONTINUOUS-TIME RECURRENT NEURAL NETWORKS
FUNAHASHI, K
NAKAMURA, Y
NEURAL NETWORKS, 1993, 6 (06) : 801 - 806
[24] A real-time learning control approach for nonlinear continuous-time system using recurrent neural networks
Chow, TWS
Li, XD
Fang, Y
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2000, 47 (02) : 478 - 486
[25] An analog VLSI recurrent neural network learning a continuous-time trajectory
Cauwenberghs, G
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1996, 7 (02): : 346 - 361
[26] Approximation of dynamical time-variant systems by continuous-time recurrent neural networks
Li, XD
Ho, JKL
Chow, TWS
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2005, 52 (10) : 656 - 660
[27] Global exponential stability in Lagrange sense of continuous-time recurrent neural networks
Liao, Xiaoxin
Zeng, Zhigang
ADVANCES IN NEURAL NETWORKS - ISNN 2006, PT 1, 2006, 3971 : 115 - 121
[28] Homeostatic plasticity improves signal propagation in continuous-time recurrent neural networks
Williams, Hywel
Noble, Jason
BIOSYSTEMS, 2007, 87 (2-3) : 252 - 259
[29] A CONVERGENCE RESULT FOR LEARNING IN RECURRENT NEURAL NETWORKS
KUAN, CM
HORNIK, K
WHITE, H
NEURAL COMPUTATION, 1994, 6 (03) : 420 - 440
[30] Convergence result for learning in recurrent neural networks
Kuan, Chung-Ming
Hornik, Kurt
White, Halbert
Neural Computation, 1994, 6 (03)

← 1 2 3 4 5 →