Learnable evolution model: Difference between revisions

Revision as of 06:14, 26 December 2013

Latest revision as of 03:12, 9 October 2024

(15 intermediate revisions by 12 users not shown)

Line 1:

{{Original research|date=September 2007}}

The '''Learnablelearnable Evolutionevolution Modelmodel''' ('''LEM''') is a novel, non-[[Darwinian]] methodology for [[evolutionary computation]] that employs [[machine learning]] to guide the generation of new individuals ([[candidate solution|candidate problem solution]]s). Unlike standard, Darwinian-type evolutionary computation methods that use random or semi-random operators for generating new individuals (such as [[mutation (genetic algorithm)|mutation]]s and/or [[genetic recombination|recombination]]s), LEM employs hypothesis generation and instantiation operators.

The [[hypothesis generation]] operator applies a machine learning program to induce descriptions that distinguish between high-[[fitness (biology)|fitness]] and low-fitness individuals in each consecutive [[population]]. Such descriptions delineate areas in the [[Candidate solution|search space]] that most likely contain the desirable solutions. Subsequently the instantiation operator samples these areas to create new individuals.

LEM has been modified from optimization ___domain to classification ___domain by augmented LEM with ID3. (February 2013 by M. Elemam Shehab, K. Badran, M. Zaki and Gouda I. Salama).

== Selected Referencesreferences ==

* {{citation |last1=Cervone |first1=P. |last2=Franzese |title=Machine Learning for the Source Detection of Atmospheric Emissions |journal=Proceedings of the 8th Conference on Artificial Intelligence Applications to Environmental Science, Code J1.7 |___location=Atlanta, GA |date=January 2010}}

*M. Elemam Shehab (February 2013),"A Generic Feature Extraction Model using Learnable Evolution Models (LEM+ID3) ", International Journal of Computer Applications,Volume 64, Number 11.

*{{citation |last1=Wojtusiak |first1=J. |last2=Michalski |first2=R. S. |title=Proceedings of the 8th annual conference on Genetic and evolutionary computation |chapter=The LEM3 implementation of learnable evolution model and its testing on complex function optimization problems |date=2006 |___location=Seattle, WA |doi=10.1145/1143997.1144197 |page=1281|isbn=978-1595931863 |citeseerx=10.1.1.72.2298 |s2cid=6133889 }}

* {{citation |last1=Cervone |first1=P. |last2=Franzese |title=Machine Learning for the Source Detection of Atmospheric Emissions |journal=Proceedings of the 8th Conference on Artificial Intelligence Applications to Environmental Science, Code J1.7 |___location=Atlanta, GA |date=January 2010}}

*{{citation |last1=Wojtusiak |first1=J. |last2title=MichalskiInitial |first2=R.Study S.on |title=TheHandling LEM3Constrained ImplementationOptimization ofProblems in Learnable Evolution Model and Its Testing on [[complex function|Complexjournal=Proceedings Function]]of [[Optimizationthe (mathematics)|Optimization]]Graduate ProblemsStudent |journal=ProceedingsWorkshop ofat Genetic and Evolutionary Computation Conference, GECCO 2006 |___location=Seattle, WA |yeardate=July 8–12, 2006 |doi=10.1145/1143997.1144197 |page=1281}}

*{{citation |last1=Jourdan |first1=L. |last2=Corne |first2=D. |last3=Savic |first3=D. |last4=Walters |first4=G. |title=Evolutionary Multi-Criterion Optimization |chapter=Preliminary Investigation of the 'Learnable Evolution Model' for Faster/Better Multiobjective Water Systems Design |volume=3410 |pages=841–855 |year=2005|doi=10.1007/978-3-540-31880-4_58 |citeseerx=10.1.1.73.9653 |series=Lecture Notes in Computer Science |isbn=978-3-540-24983-2 }}

*{{citation |last1=Wojtusiak |first1=J. |title=Initial Study on Handling Constrained Optimization Problems in Learnable Evolution Model |journal=Proceedings of the Graduate Student Workshop at Genetic and Evolutionary Computation Conference, GECCO 2006 |___location=Seattle, WA |year=July 8–12, 2006}}

*{{citation |last1=JourdanDomanski |first1=LP. A. |last2=CorneYashar |first2=D. |last3=SavicKaufman |first3=DK. |last4=WaltersMichalski |first4=GR. S. |title=PreliminaryAn InvestigationOptimized Design of theFinned-Tube ‘LearnableEvaporators EvolutionUsing Model’the forLearnable Faster/BetterEvolution Multiobjective Water Systems DesignModel |journal=ProceedingsInternational Journal of theHeating, ThirdVentilating, Int.Air-Conditioning Conferenceand onRefrigerating EvolutionaryResearch Multi-Criterion|volume=10 Optimization, EMO’05|pages=201–211 |yeardate=2005April 2004}}

*{{citation |last1=DomanskiKaufman |first1=P. AK. |last2=YasharMichalski |first2=D. |last3=Kaufman |first3=K. |last4=Michalski |first4=R. S. |title=AnApplying OptimizedLearnable DesignEvolution ofModel Finned-Tubeto EvaporatorsHeat UsingExchanger the Learnable Evolution ModelDesign |journal=InternationalProceedings Journalof ofthe Heating,Seventeenth Ventilating,National AirConference on Artificial Intelligence (AAAI-Conditioning2000) and RefrigeratingTwelfth ResearchAnnual |volume=10Conference on Innovative Applications of Artificial Intelligence (IAAI-2000) |pages=201–2111014–1019 |year=April, 20042000}}

*{{citationCite book|last1=KaufmanCervone |first1=KG. |last2=Michalski |first2=R. S. |titlelast3=ApplyingKaufman Learnable|first3=K. Evolution Model to Heat Exchanger DesignA. |journaltitle=Proceedings of the Seventeenth2000 National ConferenceCongress on ArtificialEvolutionary IntelligenceComputation. CEC00 (AAAI-2000Cat. No.00TH8512) and|chapter=Experimental Twelfthvalidations Annualof Conferencethe onlearnable Innovativeevolution Applicationsmodel of|pages=1064–1071 Artificial|date=July Intelligence (IAAI-2000)|volume=2 |___locationdoi=Austin, TX10.1109/CEC.2000.870765 |pagesisbn=1014–10190-7803-6375-2 |years2cid=20003149132 }}

*{{citation |last1=CervoneMichalski |first1=G. |last2=Michalski |first2=R. S. |last3title=KaufmanLEARNABLE |first3=K.EVOLUTION A.MODEL |title=ExperimentalEvolutionary ValidationsProcesses ofGuided theby LearnableMachine Evolution ModelLearning |journal=2000 Congress on EvolutionaryMachine ComputationLearning |___locationvolume=San Diego CA38 |pages=1064–10719–40 |dateyear=July2000 |doi=10.1023/A:1007677805582|doi-access=free 2000}}

*{{citation |last1=Michalski |first1=R. .S. |title=LEARNABLELearnable EVOLUTIONEvolution: MODELCombining EvolutionarySymbolic Processesand Guided by MachineEvolutionary Learning |journal=MachineProceedings of the Fourth International Workshop on Multistrategy Learning |volume=38(MSL'98) |pages=9–4014–20 |yeardate=2000June |doi=10.1023/A:100767780558211–13, 1998}}

*{{citation |last1=MichalskiH Yar|first1=R .SM. |title=LearnableA Evolution:survey Combiningon Symbolicevolutionary andcomputation: EvolutionaryMethods Learningand |journal=Proceedingstheir ofapplications thein Fourth International Workshop on [[Multistrategy]] Learning (MSL'98)engineering |___locationjournal=DesenzanoMod. delAppl. Garda,Sci Italy |pages=14–20 |yeardate=June 11–13, 19982016}}

[[Category:Evolutionary computation]]