Pregled bibliografske jedinice broj: 903531
On the mutual information as a fitness landscape measure
On the mutual information as a fitness landscape measure // GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion
New York (NY): AMC, 2017. str. 165-166 (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 903531 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
On the mutual information as a fitness landscape
measure
Autori
Čorić, Rebeka ; Picek, Stjepan ; Jakobović, Domagoj ; Coello Coello, Carlos A.
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
GECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion
/ - New York (NY) : AMC, 2017, 165-166
ISBN
978-1-4503-4939-0
Skup
GECCO '17 - Genetic and Evolutionary Computation Conference
Mjesto i datum
Berlin, Njemačka, 15.07.2017. - 19.07.2017
Vrsta sudjelovanja
Poster
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Fitness landscape, Single-objective, Mutual Information, Performance comparison
Sažetak
Fitness landscape analysis plays an important role in both theoretical and practical perspectives when using evolutionarya lgorithms. In this paper, we develop a new measure based on th emutual information paradigm and we show how it can help to deduce further information about the fitness landscape. In order to validate it as a valuable source of information when conducting fitness landscape analysis, we investigate its properties on a well-known benchmark suite. Moreover, we investigate the usefulness of the obtained information when choosing crossover operators. Finally, we show that when using our new measure, a number of classifiers can be constructed that offer an improved accuracy.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb,
Sveučilište u Osijeku, Odjel za matematiku
