Neural Networks Elitist Evolution
Material type:
ArticleDescription: Datos electrónicos (1 archivo: 208 KB)Subject(s): Summary: This paper presents an elitist evolving strategy, which allows obtaining a controller, based on a neural network capable of commanding an autonomous robot. In order to reduce the detrimental crossover effect, we propose to use a strategy to create several children for each parent pair, selecting properly the way of making the replacement. The results obtained that, though the number ofchildren is high, the quantity of fitness tests carried out is actually lower than that of aconventional evolving algorithm. In this way, we propose an alternative that reduces thecomputational cost of the process, reaching at a suitable response for the problem resolution.
| Item type | Home library | Call number | Status | Date due | Barcode | |
|---|---|---|---|---|---|---|
Capítulo de libro
|
Biblioteca de la Facultad de Informática | A0228 (Browse shelf(Opens below)) | No corresponde |
Browsing Biblioteca de la Facultad de Informática shelves Close shelf browser (Hides shelf browser)
Formato de archivo: PDF. -- Este documento es producción intelectual de la Facultad de Informática-UNLP (Colección BIPA / Biblioteca.)
This paper presents an elitist evolving strategy, which allows obtaining a controller, based on a neural network capable of commanding an autonomous robot. In order to reduce the detrimental crossover effect, we propose to use a strategy to create several children for each parent pair, selecting properly the way of making the replacement. The results obtained that, though the number ofchildren is high, the quantity of fitness tests carried out is actually lower than that of aconventional evolving algorithm. In this way, we propose an alternative that reduces thecomputational cost of the process, reaching at a suitable response for the problem resolution.
International Conference on Information Technology Interfaces (29th : 2007 : Duvrovnik)