Improving learning performance through rational resource allocation

Jonathan Gratch, Steve Chien, Gerald F DeJong

Research output: Contribution to conferencePaper

Abstract

This article shows how rational analysis can be used to minimize learning cost for a general class of statistical learning problems. We discuss the factors that influence learning cost and show that the problem of efficient learning can be cast as a resource optimization problem. Solutions found in this way can be significantly more efficient than the best solutions that do not account for these factors. We introduce a heuristic learning algorithm that approximately solves this optimization problem and document its performance improvements on synthetic and real-world problems.

Original languageEnglish (US)
Pages576-581
Number of pages6
StatePublished - Dec 1 1994
EventProceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2) - Seattle, WA, USA
Duration: Jul 31 1994Aug 4 1994

Other

OtherProceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2)
CitySeattle, WA, USA
Period7/31/948/4/94

Fingerprint

Resource allocation
Heuristic algorithms
Learning algorithms
Costs

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Gratch, J., Chien, S., & DeJong, G. F. (1994). Improving learning performance through rational resource allocation. 576-581. Paper presented at Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2), Seattle, WA, USA, .

Improving learning performance through rational resource allocation. / Gratch, Jonathan; Chien, Steve; DeJong, Gerald F.

1994. 576-581 Paper presented at Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2), Seattle, WA, USA, .

Research output: Contribution to conferencePaper

Gratch, J, Chien, S & DeJong, GF 1994, 'Improving learning performance through rational resource allocation', Paper presented at Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2), Seattle, WA, USA, 7/31/94 - 8/4/94 pp. 576-581.
Gratch J, Chien S, DeJong GF. Improving learning performance through rational resource allocation. 1994. Paper presented at Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2), Seattle, WA, USA, .
Gratch, Jonathan ; Chien, Steve ; DeJong, Gerald F. / Improving learning performance through rational resource allocation. Paper presented at Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2), Seattle, WA, USA, .6 p.
@conference{7e62094e4c4b483fb581ee21815861a1,
title = "Improving learning performance through rational resource allocation",
abstract = "This article shows how rational analysis can be used to minimize learning cost for a general class of statistical learning problems. We discuss the factors that influence learning cost and show that the problem of efficient learning can be cast as a resource optimization problem. Solutions found in this way can be significantly more efficient than the best solutions that do not account for these factors. We introduce a heuristic learning algorithm that approximately solves this optimization problem and document its performance improvements on synthetic and real-world problems.",
author = "Jonathan Gratch and Steve Chien and DeJong, {Gerald F}",
year = "1994",
month = "12",
day = "1",
language = "English (US)",
pages = "576--581",
note = "Proceedings of the 12th National Conference on Artificial Intelligence. Part 1 (of 2) ; Conference date: 31-07-1994 Through 04-08-1994",

}

TY - CONF

T1 - Improving learning performance through rational resource allocation

AU - Gratch, Jonathan

AU - Chien, Steve

AU - DeJong, Gerald F

PY - 1994/12/1

Y1 - 1994/12/1

N2 - This article shows how rational analysis can be used to minimize learning cost for a general class of statistical learning problems. We discuss the factors that influence learning cost and show that the problem of efficient learning can be cast as a resource optimization problem. Solutions found in this way can be significantly more efficient than the best solutions that do not account for these factors. We introduce a heuristic learning algorithm that approximately solves this optimization problem and document its performance improvements on synthetic and real-world problems.

AB - This article shows how rational analysis can be used to minimize learning cost for a general class of statistical learning problems. We discuss the factors that influence learning cost and show that the problem of efficient learning can be cast as a resource optimization problem. Solutions found in this way can be significantly more efficient than the best solutions that do not account for these factors. We introduce a heuristic learning algorithm that approximately solves this optimization problem and document its performance improvements on synthetic and real-world problems.

UR - http://www.scopus.com/inward/record.url?scp=0028605138&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028605138&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0028605138

SP - 576

EP - 581

ER -