In this study, we introduce a new neural architecture called N4 that is based on a collection of local receptive elds realized in the form of referential neural networks. While the network exhibits some similarities to other structures of modular neural networks (such as expert networks), it comes with a number of unique features. Especially, its receptive elds exhibit high 6exibility by being formed by neural networks. Subsequently, the processing therein is of referential nature. A ”skeleton” (structure) of the network is completed through unsupervised learning that is aimed at “discovering” and structuring the main dependencies in data. More speci cally, the design of the network consists of two phases. First, a blueprint of the network is formed and this involves the prototypes obtained through clustering of training data. This structural development of the network is followed by further re nement in a form of parametric training of the individual neural receptive elds. The study provides a detailed analysis and learning of the network and includes experimental investigations.

Pedrycz W, Chun G, Succi G (2003). N4-Computing with neuro-receptive fields. NEUROCOMPUTING, 55(1-2), 383-401.

N4-Computing with neuro-receptive fields

Succi G
2003

Abstract

In this study, we introduce a new neural architecture called N4 that is based on a collection of local receptive elds realized in the form of referential neural networks. While the network exhibits some similarities to other structures of modular neural networks (such as expert networks), it comes with a number of unique features. Especially, its receptive elds exhibit high 6exibility by being formed by neural networks. Subsequently, the processing therein is of referential nature. A ”skeleton” (structure) of the network is completed through unsupervised learning that is aimed at “discovering” and structuring the main dependencies in data. More speci cally, the design of the network consists of two phases. First, a blueprint of the network is formed and this involves the prototypes obtained through clustering of training data. This structural development of the network is followed by further re nement in a form of parametric training of the individual neural receptive elds. The study provides a detailed analysis and learning of the network and includes experimental investigations.
2003
Pedrycz W, Chun G, Succi G (2003). N4-Computing with neuro-receptive fields. NEUROCOMPUTING, 55(1-2), 383-401.
Pedrycz W; Chun G; Succi G
File in questo prodotto:
Eventuali allegati, non sono esposti

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/894144
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? ND
social impact