Szczegóły publikacji
Opis bibliograficzny
Co-evolution of fitness predictors and deep neural networks / Włodzimierz FUNIKA, Paweł Koperek // W: Parallel Processing and Applied Mathematics : 12th international conference, PPAM 2017 : Lublin, Poland, September 10–13, 2017 : revised selected papers, Pt. 1 / eds. Roman Wyrzykowski [et al.]. — Cham: Springer International Publishing, cop. 2018. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 10777. Theoretical Computer Science and General Issues ; ISSN 0302-9743). — ISBN: 978-3-319-78023-8; e-ISBN: 978-3-319-78024-5. — S. 555–564. — Bibliogr. s. 563–564, Abstr. — Publikacja dostępna online od: 2018-03-23
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 120670 |
|---|---|
| Data dodania do BaDAP | 2019-04-18 |
| Tekst źródłowy | URL |
| DOI | 10.1007/978-3-319-78024-5_48 |
| Rok publikacji | 2018 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | Parallel Processing and Applied Mathematics : 12th international conference |
| Czasopisma/serie | Lecture Notes in Computer Science, Theoretical Computer Science and General Issues |
Abstract
Deep neural networks proved to be a very useful and powerful tool with many applications. In order to achieve good learning results, the network architecture has, however, to be carefully designed, which requires a lot of experience and knowledge. Using an evolutionary process to develop new network topologies can facilitate this process. The limiting factor is the speed of evaluation of a single specimen (a single network architecture), which includes learning based on a large dataset. In this paper we propose a new approach which uses subsets of the original training set to approximate the fitness. We describe a co-evolutionary algorithm and discuss its key elements. Finally we draw conclusions from experiments and outline plans for future work.