Experimental validations of the learnable evolution model

Guido Cervone, Kenneth K. Kaufman, Ryszard S. Michalski

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

A recently developed approach to evolutionary computation, called Learnable Evolution Model or LEM, employs machine learning to guide processes of generating new populations. The central new idea of LEM is that it generates new individuals not by mutation and/or recombination, but by processes of hypothesis generation and instantiation. The hypotheses are generated by a machine learning system from examples of high and low performance individuals. When applied to problems of function optimization and parameter estimation for nonlinear filters, LEM significantly outperformed the standard evolutionary computation algorithms used in experiments, sometimes achieving two or more orders of magnitude of evolutionary speed-up (in terms of the number of births). An application of LEM to the problem of optimizing heat exchangers has produced designs equal to or exceeding the best human designs. Further research needs to explore trade-offs and determine best areas for LEM application.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Conference on Evolutionary Computation, ICEC
Pages1064-1071
Number of pages8
Volume2
StatePublished - 2000
EventProceedings of the 2000 Congress on Evolutionary Computation - California, CA, USA
Duration: Jul 16 2000Jul 19 2000

Other

OtherProceedings of the 2000 Congress on Evolutionary Computation
CityCalifornia, CA, USA
Period7/16/007/19/00

Fingerprint

Learning systems
Evolutionary algorithms
Parameter estimation
Heat exchangers
Experiments

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science(all)
  • Computational Theory and Mathematics

Cite this

Cervone, G., Kaufman, K. K., & Michalski, R. S. (2000). Experimental validations of the learnable evolution model. In Proceedings of the IEEE Conference on Evolutionary Computation, ICEC (Vol. 2, pp. 1064-1071)
Cervone, Guido ; Kaufman, Kenneth K. ; Michalski, Ryszard S. / Experimental validations of the learnable evolution model. Proceedings of the IEEE Conference on Evolutionary Computation, ICEC. Vol. 2 2000. pp. 1064-1071
@inproceedings{b8b387839b6c48ebbfd61d8906806963,
title = "Experimental validations of the learnable evolution model",
abstract = "A recently developed approach to evolutionary computation, called Learnable Evolution Model or LEM, employs machine learning to guide processes of generating new populations. The central new idea of LEM is that it generates new individuals not by mutation and/or recombination, but by processes of hypothesis generation and instantiation. The hypotheses are generated by a machine learning system from examples of high and low performance individuals. When applied to problems of function optimization and parameter estimation for nonlinear filters, LEM significantly outperformed the standard evolutionary computation algorithms used in experiments, sometimes achieving two or more orders of magnitude of evolutionary speed-up (in terms of the number of births). An application of LEM to the problem of optimizing heat exchangers has produced designs equal to or exceeding the best human designs. Further research needs to explore trade-offs and determine best areas for LEM application.",
author = "Guido Cervone and Kaufman, {Kenneth K.} and Michalski, {Ryszard S.}",
year = "2000",
language = "English (US)",
volume = "2",
pages = "1064--1071",
booktitle = "Proceedings of the IEEE Conference on Evolutionary Computation, ICEC",

}

Cervone, G, Kaufman, KK & Michalski, RS 2000, Experimental validations of the learnable evolution model. in Proceedings of the IEEE Conference on Evolutionary Computation, ICEC. vol. 2, pp. 1064-1071, Proceedings of the 2000 Congress on Evolutionary Computation, California, CA, USA, 7/16/00.

Experimental validations of the learnable evolution model. / Cervone, Guido; Kaufman, Kenneth K.; Michalski, Ryszard S.

Proceedings of the IEEE Conference on Evolutionary Computation, ICEC. Vol. 2 2000. p. 1064-1071.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Experimental validations of the learnable evolution model

AU - Cervone, Guido

AU - Kaufman, Kenneth K.

AU - Michalski, Ryszard S.

PY - 2000

Y1 - 2000

N2 - A recently developed approach to evolutionary computation, called Learnable Evolution Model or LEM, employs machine learning to guide processes of generating new populations. The central new idea of LEM is that it generates new individuals not by mutation and/or recombination, but by processes of hypothesis generation and instantiation. The hypotheses are generated by a machine learning system from examples of high and low performance individuals. When applied to problems of function optimization and parameter estimation for nonlinear filters, LEM significantly outperformed the standard evolutionary computation algorithms used in experiments, sometimes achieving two or more orders of magnitude of evolutionary speed-up (in terms of the number of births). An application of LEM to the problem of optimizing heat exchangers has produced designs equal to or exceeding the best human designs. Further research needs to explore trade-offs and determine best areas for LEM application.

AB - A recently developed approach to evolutionary computation, called Learnable Evolution Model or LEM, employs machine learning to guide processes of generating new populations. The central new idea of LEM is that it generates new individuals not by mutation and/or recombination, but by processes of hypothesis generation and instantiation. The hypotheses are generated by a machine learning system from examples of high and low performance individuals. When applied to problems of function optimization and parameter estimation for nonlinear filters, LEM significantly outperformed the standard evolutionary computation algorithms used in experiments, sometimes achieving two or more orders of magnitude of evolutionary speed-up (in terms of the number of births). An application of LEM to the problem of optimizing heat exchangers has produced designs equal to or exceeding the best human designs. Further research needs to explore trade-offs and determine best areas for LEM application.

UR - http://www.scopus.com/inward/record.url?scp=0033671770&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033671770&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0033671770

VL - 2

SP - 1064

EP - 1071

BT - Proceedings of the IEEE Conference on Evolutionary Computation, ICEC

ER -

Cervone G, Kaufman KK, Michalski RS. Experimental validations of the learnable evolution model. In Proceedings of the IEEE Conference on Evolutionary Computation, ICEC. Vol. 2. 2000. p. 1064-1071