In this paper, a 1 newefficientmodel of neural network is proposed,which is realized by the combination of two recent and successful neurocomputing paradigms. The idea behind the work is to realize a neural network constituted by multi-valued complex neurons, which are trained with the principles of extreme learning machine (ELM). The specific kind of used neuron allows a very straightforward derivation of the ELM, with no substantialmodification in the weight adjustment procedure. The main advantages that clearly emerge by this model are represented by the further increasing of generalization performances in presence of noise, together with a generalized reduction of needed nodes (neurons) in the hidden layer. The effectiveness of the proposedmodelwill be shown by some benchmark results, also compared with the original techniques.

A Multi-Valued Neuron Based Complex ELM Neural Network / Grasso, Francesco; Luchetta, Antonio; Manetti, Stefano. - In: NEURAL PROCESSING LETTERS. - ISSN 1370-4621. - ELETTRONICO. - .:(2017), pp. 1-13. [10.1007/s11063-017-9745-9]

A Multi-Valued Neuron Based Complex ELM Neural Network

Grasso, Francesco;Luchetta, Antonio
;
Manetti, Stefano
2017

Abstract

In this paper, a 1 newefficientmodel of neural network is proposed,which is realized by the combination of two recent and successful neurocomputing paradigms. The idea behind the work is to realize a neural network constituted by multi-valued complex neurons, which are trained with the principles of extreme learning machine (ELM). The specific kind of used neuron allows a very straightforward derivation of the ELM, with no substantialmodification in the weight adjustment procedure. The main advantages that clearly emerge by this model are represented by the further increasing of generalization performances in presence of noise, together with a generalized reduction of needed nodes (neurons) in the hidden layer. The effectiveness of the proposedmodelwill be shown by some benchmark results, also compared with the original techniques.
2017
.
1
13
Grasso, Francesco; Luchetta, Antonio; Manetti, Stefano
File in questo prodotto:
File Dimensione Formato  
pubblicato.pdf

Accesso chiuso

Descrizione: Articolo principale
Tipologia: Pdf editoriale (Version of record)
Licenza: Creative commons
Dimensione 460.3 kB
Formato Adobe PDF
460.3 kB Adobe PDF   Richiedi una copia

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

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1105086
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 16
  • ???jsp.display-item.citation.isi??? 11
social impact