Szczegóły publikacji
Opis bibliograficzny
Application of the Hierarchic Memetic Strategy HMS in neuroevolution / Mateusz Sokół, Maciej SMOŁKA // W: Computational Science – ICCS 2022 : 22nd international conference : London, UK, June 21–23, 2022 : proceedings, Pt. 2 / eds. Derek Groen, [et al.]. — Cham : Springer Nature Switzerland, cop. 2022. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 13351). — ISBN: 978-3-031-08753-0; e-ISBN: 978-3-031-08754-7. — S. 422–429. — Bibliogr., Abstr. — Publikacja dostępna online od: 2022-06-15
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
ID BaDAP | 140667 |
---|---|
Data dodania do BaDAP | 2022-06-24 |
DOI | 10.1007/978-3-031-08754-7_49 |
Rok publikacji | 2022 |
Typ publikacji | materiały konferencyjne (aut.) |
Otwarty dostęp | |
Wydawca | Springer |
Konferencja | 22nd International Conference on Computational Science |
Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
Quite recently some noteworthy papers appeared showing classes of deep neural network (DNN) training tasks where rather simple one-population evolutionary algorithms (EA) found better solutions than gradient-based optimization methods. However, it is well known that simple single-population evolutionary algorithms generally suffer from the problem of getting stuck in local optima. A multi-population adaptive evolutionary strategy called Hierarchic Memetic Strategy (HMS) is designed especially to mitigate this problem. HMS was already shown to outperform single-population EAs in general multi-modal optimization and in inverse problem solving. In this paper we describe an application of HMS to the DNN training tasks where the above-mentioned single-population EA won over gradient methods. Obtained results show that HMS finds better solutions than the EA when using the same time resources, therefore proving the advantage of HMS over not only the EA but in consequence also over gradient methods.