Pregled bibliografske jedinice broj: 10255
The use of genetic algorithms in the optimization of competitive neural networks which resolve the stuck vectors problem
The use of genetic algorithms in the optimization of competitive neural networks which resolve the stuck vectors problem // Proceedings of the first annual conference: Genetic Programming / Koza, John R ; Goldberg, David E ; Fogel, D.B ; Riolo, R.L. (ur.).
Stanford (CA), Sjedinjene Američke Države: Stanford University, 1996. str. 499-499 (poster, međunarodna recenzija, sažetak, znanstveni)
CROSBI ID: 10255 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
The use of genetic algorithms in the optimization of competitive neural networks which resolve the stuck vectors problem
Autori
Ilakovac, Tin ; Perković, Željka ; Ristov, Strahil
Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni
Izvornik
Proceedings of the first annual conference: Genetic Programming
/ Koza, John R ; Goldberg, David E ; Fogel, D.B ; Riolo, R.L. - : Stanford University, 1996, 499-499
Skup
The first annual conference: Genetic Programming
Mjesto i datum
Stanford (CA), Sjedinjene Američke Države, 28.07.1996. - 31.07.1996
Vrsta sudjelovanja
Poster
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
genetic algorithms; neural networks
Sažetak
We show that for variable rates of mutation and crossover that depend on the global fitness of the population, and selection of reproduction pair that is asymmetric, solutions to problems with stringent constraints are found.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
