Digitale Bibliotheek
Sluiten Bladeren door artikelen uit een tijdschrift
 
<< vorige    volgende >>
     Tijdschrift beschrijving
       Alle jaargangen van het bijbehorende tijdschrift
         Alle afleveringen van het bijbehorende jaargang
           Alle artikelen van de bijbehorende aflevering
                                       Details van artikel 2 van 11 gevonden artikelen
 
 
  Differential Polynomial Neural Network
 
 
Titel: Differential Polynomial Neural Network
Auteur: L. Zjavka
Verschenen in: Journal of artificial intelligence
Paginering: Jaargang 4 (2011) nr. 1 pagina's 89-99
Jaar: 2011
Inhoud: Artificial neural network identification in general is based on pattern similarity and absolute values of input variables, but these can differ enormously while their relations may be the same. Generalization (learning) of these dependencies could be a way of modelling systems more similar to human brain learning than a pattern classification. Differential polynomial neural network is a new type of neural network developed by author, which constructs a differential equation, describing system of dependent variables. It creates derivative fractional terms defining a mutual change of some input variable combinations. Its response should be the same to all input patterns, which variables behave the trained dependence (regardless of their values). The most important function of brain seems to be a generalization of received information, i.e., forming ideas of common validity from received data. How does a biological neural cell process information and how it functionality essentially differs from artificial neuron ? It seems to create some polynomial multi-parametric functions, which could be better modeled by polynomial neuron. It should describe the partial dependence of some combinations of variables, using a special type of simple polynomial functions. However neural cell applies periodic activation function to create derivative terms of which differential equation describing data relations consists.
Uitgever: Asian Network for Scientific Information (provided by DOAJ)
Bronbestand: Elektronische Wetenschappelijke Tijdschriften
 
 

                             Details van artikel 2 van 11 gevonden artikelen
 
<< vorige    volgende >>
 
 Koninklijke Bibliotheek - Nationale Bibliotheek van Nederland