Donnarumma, Francesco and Prevete, Roberto and Trautteur, Giuseppe (2012) Programming in the brain: a neural network theoretical framework. [Pubblicazione in rivista scientifica]

Testo 09540091.2012.pdf Visibile a [TBR] Amministratori dell'archivio Download (9MB)

[error in script] [error in script]

Tipologia del documento:	Pubblicazione in rivista scientifica
Lingua:	English
Titolo:	Programming in the brain: a neural network theoretical framework
Autori:	Autore Email Donnarumma, Francesco [non definito] Prevete, Roberto prevete@na.infn.it Trautteur, Giuseppe [non definito]
Data:	2012
Istituzione:	Università degli Studi di Napoli Federico II
Dipartimento:	Dipartimento di Scienze Fisiche
URL ufficiale:	http://dx.doi.org/10.1080/09540091.2012.684670
Titolo del periodico:	Connection Science
Editore:	Taylor & Francis
Data:	2012
ISSN:	0954-0091 (print); 1360-0494 (online)
Volume:	Vol. 24, 71–90
Numero:	Nos. 2–3, June–September 2012
Intervallo di pagine:	pp. 71-90
Parole chiave:	programmable neural networks; CTRNN; fixed-weight network; programmability; biologically plausible neural architecture
Diritti di accesso:	Accesso ristretto
Informazioni aggiuntive:	AIRobots
Depositato il:	12 Set 2014 09:17
Ultima modifica:	17 Mag 2017 17:31
URI:	http://www.fedoa.unina.it/id/eprint/9615

Abstract

Recent research shows that some brain areas perform more than one task and the switching times between them are incompatible with learning and that parts of the brain are controlled by other parts of the brain, or are “recycled”, or are used and reused for various purposes by other neural circuits in different task categories and cognitive domains. All this is conducive to the notion of “programming in the brain”. In this paper, we describe a programmable neural architecture, biologically plausible on the neural level, and we implement, test, and validate it in order to support the programming interpretation of the above-mentioned phenomenology.A programmable neural network is a fixed-weight network that is endowed with auxiliary or programming inputs and behaves as any of a specified class of neural networks when its programming inputs are fed with a code of the weight matrix of a network of the class. The construction is based on the “pulling out” of the multiplication between synaptic weights and neuron outputs and having it performed in “software” by specialised multiplicative-response fixed subnetworks. Such construction has been tested for robustness with respect to various sources of noise. Theoretical underpinnings, analysis of related research, detailed construction schemes, and extensive testing results are given.

Downloads

Actions (login required)

Modifica documento