Szczegóły publikacji
Opis bibliograficzny
Mitigating saturation in Fuzzy-Flip-Flop Neural Networks trained with memetic PSO algorithm / Piotr A. KOWALSKI, Tomasz Słoczyński // W: FUZZ-IEEE 2024 [Dokument elektroniczny] : 2024 IEEE International conference on Fuzzy Systems : [30 June 2024 - 05 July 2024, Yokohama, Japan] : proceedings. — Wersja do Windows. — Dane tekstowe. — [Piscataway] : IEEE, cop. 2024. — ( IEEE International Fuzzy Systems Conference Proceedings ; ISSN 1544-5615 ). — Dod. ISBN: 979-8-3503-1955-2 (print on demand). — e-ISBN: 979-8-3503-1954-5. — S. [1–8]. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. [8], Abstr. — Publikacja dostępna online od: 2024-08-05. — P. A. Kowalski - dod. afiliacja: Systems Research Institute, Polish Academy of Sciences, Warsaw, Poland
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 158338 |
|---|---|
| Data dodania do BaDAP | 2025-02-25 |
| Tekst źródłowy | URL |
| DOI | 10.1109/FUZZ-IEEE60900.2024.10611809 |
| Rok publikacji | 2024 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Institute of Electrical and Electronics Engineers (IEEE) |
| Konferencja | IEEE International Conference on Fuzzy Systems 2024 |
| Czasopismo/seria | IEEE International Fuzzy Systems conference proceedings |
Abstract
This paper investigates the efficacy of learning algorithms for training Fuzzy Flip-Flop Neural Networks, focusing on Particle Swarm Optimization (PSO) and memetic PSO variants. The study explores their performance across diverse datasets, including Breast Cancer Wisconsin, Seeds, and Glass. Results demonstrate that memetic PSO variants, consistently outperform other algorithms in terms of classification accuracy and reduced saturation levels. The examination of different crossover strategies within the memetic PSO framework provides insights into their impact on learning performance. Overall, this research highlights the superiority of memetic PSO algorithms in optimising Fuzzy Flip-Flop Neural Networks for classification tasks with complex datasets, suggesting their potential for broader applications. © 2024 IEEE.
