Szczegóły publikacji
Opis bibliograficzny
From homogeneous network to neural nets with fractional derivative mechanism / Zbigniew Gomółka, Ewa DUDEK-DYDUCH, Yuriy P. Kondratenko // W: Artificial Intelligence and Soft Computing : 16th International Conference : ICAISC 2017 Zakopane, Poland, June 11–15, 2017 : proceedings, Pt. 1 / eds. Leszek Rutkowski, [et al.]. — Switzerland : Springer International Publishing, cop. 2017. — (Lecture Notes in Computer Science ; ISSN 0302-9743. Lecture Notes in Artificial Intelligence ; LNAI 10245). — Toż na Dysku Flash. — ISBN: 978-3-319-59062-2; e-ISBN: 978-3-319-59063-9. — S. 52–63. — Bibliogr. s. 62–63, Abstr. — Publikacja dostępna online od: 2017-05-27. — Z. Gomółka - afiliacja: Uniwersytet Rzeszowski
Autorzy (3)
- Gomółka Zbigniew
- AGHDudek-Dyduch Ewa
- Kondratenko Yuriy P.
Dane bibliometryczne
ID BaDAP | 106540 |
---|---|
Data dodania do BaDAP | 2017-06-28 |
Tekst źródłowy | URL |
DOI | 10.1007/978-3-319-59063-9_5 |
Rok publikacji | 2017 |
Typ publikacji | materiały konferencyjne (aut.) |
Otwarty dostęp | |
Wydawca | Springer |
Konferencja | 16th International Conference on Artificial Intelligence and Soft Computing |
Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
The paper refers to ANNs of the feed-forward type, homogeneous within individual layers. It extends the idea of network modelling and design with the use of calculus of finite differences proposed by Dudek-Dyduch E. and then developed jointly with Tadeusiewicz R. and others. This kind of neural nets was applied mainly to different features extraction i.e. edges, ridges, maxima, extrema and many others that can be defined with the use of classic derivative of any order and their linear combinations. Authors extend this type ANNs modelling by using fractional derivative theory. The formulae for weight distribution functions expressed by means of fractional derivative and its discrete approximation are given. It is also shown that the application of discrete approximation of fractional derivative of some base functions allows for modelling the transfer function of a single neuron for various characteristics. In such an approach smooth control of a derivative order allows to model the neuron dynamics without direct modification of the source code in IT model. The new approach presented in the paper, universalizes the model of the considered type of ANNs.