Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloDynamic Network Functional Comparison via Approximate-bisimulation
Anno di pubblicazione2015
FormatoCartaceo
Autore/iFrancesco Donnarumma, Aniello Murano, Roberto Prevete.
Affiliazioni autoriCNR-ISTC, Università di Napoli Federico II
Autori CNR e affiliazioni
  • FRANCESCO DONNARUMMA
Lingua/e
  • inglese
AbstractIt is generally unknown how to formally determine whether different neural networks have a similar behaviour. This question intimately relates to the problem of finding a suitable similarity measure to identify bounds on the input-output response distances of neural networks, which has several interesting theoretical and computational implications. For example, it can allow one to speed up the learning processes by restricting the network parameter space, or to test the robustness of a network with respect to parameter variation. In this paper we develop a procedure that allows for comparing neural structures among them. In particular, we consider dynamic networks composed of neural units, characterised by non-linear differential equations, described in terms of autonomous continuous dynamic systems. The comparison is established by importing and adapting from the formal verification setting the concept of ?-approximate bisimulations techniques for non-linear systems. We have positively tested the proposed approach over continuous time recurrent neural networks (CTRNNs).
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da99
Pagine a127
Pagine totali29
RivistaControl and Cybernetics
Attiva dal 1972
Editore: Panstwowe Wydawnictwo Naukowe. - Warszawa
Paese di pubblicazione: Polonia
Lingua: inglese
ISSN: 0324-8569
Titolo chiave: Control and Cybernetics
Titolo abbreviato: Control Cybern.
Numero volume della rivista44
Fascicolo della rivista1
DOI-
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)-
Parole chiavecontinuous time recurrent neural network, dynamic networks, bisimulation, network equivalence
Link (URL, URI)http://control.ibspan.waw.pl:3000/contents/export?filename=donnarumma-et-al.pdf
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione-
Note/Altre informazioni-
Strutture CNR
  • ISTC — Istituto di scienze e tecnologie della cognizione
Moduli/Attività/Sottoprogetti CNR-
Progetti Europei
Allegati