Numerical optimization with neuroevolution

Brian Greer, Henri Hakonen, Risto Lahdelma, Risto Miikkulainen

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

15 Citations (Scopus)

Abstract

Neuroevolution techniques have been successful in many sequential decision tasks, such as robot control and game playing. This paper aims at establishing whether they can be useful in numerical optimization more generally, by comparing neuroevolution to linear programming in a manufacturing optimization domain. It turns out that neuroevolution can learn to compensate for uncertainty in the data and outperform linear programming when the number of variables in the problem is small and the required precision is low, but the current techniques do not (yet) provide an advantage in problems where many variables must be optimized with high precision.

Original languageEnglish
Title of host publicationProceedings of the 2002 Congress on Evolutionary Computation, CEC 2002
PublisherIEEE
Pages396-401
Number of pages6
Volume1
ISBN (Print)0-7803-7282-4
DOIs
Publication statusPublished - 2002
MoE publication typeA4 Conference publication
EventIEEE Congress on Evolutionary Computation - Honolulu, United States
Duration: 12 May 200217 May 2002

Conference

ConferenceIEEE Congress on Evolutionary Computation
Abbreviated titleCEC
Country/TerritoryUnited States
CityHonolulu
Period12/05/200217/05/2002

Fingerprint

Dive into the research topics of 'Numerical optimization with neuroevolution'. Together they form a unique fingerprint.

Cite this