The functional link net and learning optimal control

Yoh Han Pao, Stephen Phillips

Research output: Contribution to journalArticle

55 Citations (Scopus)

Abstract

We present a strategy for learning optimal control. The approach uses functional-link neural network implementations which have several beneficial properties giving advantages over the more common generalized delta rule implementations. The learning task is decomposed into three parts: identification and monitoring, one-step-ahead control generation, and control path optimization. Each of these parts is accomplished with its own functional-link net and these are coordinated to provide the real-time learning of the optimal control path.

Original languageEnglish (US)
Pages (from-to)149-164
Number of pages16
JournalNeurocomputing
Volume9
Issue number2
DOIs
StatePublished - 1995
Externally publishedYes

Fingerprint

Learning
Neural networks
Monitoring

Keywords

  • Functional-link net
  • Neural net control
  • Optimal control
  • Real-time learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Cognitive Neuroscience
  • Cellular and Molecular Neuroscience

Cite this

The functional link net and learning optimal control. / Pao, Yoh Han; Phillips, Stephen.

In: Neurocomputing, Vol. 9, No. 2, 1995, p. 149-164.

Research output: Contribution to journalArticle

Pao, Yoh Han ; Phillips, Stephen. / The functional link net and learning optimal control. In: Neurocomputing. 1995 ; Vol. 9, No. 2. pp. 149-164.
@article{16d3277b775d4cbe9a5077187bf3e9c4,
title = "The functional link net and learning optimal control",
abstract = "We present a strategy for learning optimal control. The approach uses functional-link neural network implementations which have several beneficial properties giving advantages over the more common generalized delta rule implementations. The learning task is decomposed into three parts: identification and monitoring, one-step-ahead control generation, and control path optimization. Each of these parts is accomplished with its own functional-link net and these are coordinated to provide the real-time learning of the optimal control path.",
keywords = "Functional-link net, Neural net control, Optimal control, Real-time learning",
author = "Pao, {Yoh Han} and Stephen Phillips",
year = "1995",
doi = "10.1016/0925-2312(95)00066-F",
language = "English (US)",
volume = "9",
pages = "149--164",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",
number = "2",

}

TY - JOUR

T1 - The functional link net and learning optimal control

AU - Pao, Yoh Han

AU - Phillips, Stephen

PY - 1995

Y1 - 1995

N2 - We present a strategy for learning optimal control. The approach uses functional-link neural network implementations which have several beneficial properties giving advantages over the more common generalized delta rule implementations. The learning task is decomposed into three parts: identification and monitoring, one-step-ahead control generation, and control path optimization. Each of these parts is accomplished with its own functional-link net and these are coordinated to provide the real-time learning of the optimal control path.

AB - We present a strategy for learning optimal control. The approach uses functional-link neural network implementations which have several beneficial properties giving advantages over the more common generalized delta rule implementations. The learning task is decomposed into three parts: identification and monitoring, one-step-ahead control generation, and control path optimization. Each of these parts is accomplished with its own functional-link net and these are coordinated to provide the real-time learning of the optimal control path.

KW - Functional-link net

KW - Neural net control

KW - Optimal control

KW - Real-time learning

UR - http://www.scopus.com/inward/record.url?scp=0029379686&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029379686&partnerID=8YFLogxK

U2 - 10.1016/0925-2312(95)00066-F

DO - 10.1016/0925-2312(95)00066-F

M3 - Article

AN - SCOPUS:0029379686

VL - 9

SP - 149

EP - 164

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

IS - 2

ER -