Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions
Autore:
Wersing, H; Beyn, WJ; Ritter, H;
Indirizzi:
Univ Bielefeld, Fac Technol, D-33501 Bielefeld, Germany Univ Bielefeld Bielefeld Germany D-33501 nol, D-33501 Bielefeld, Germany Univ Bielefeld, Fac Math, D-33501 Bielefeld, Germany Univ Bielefeld Bielefeld Germany D-33501 ath, D-33501 Bielefeld, Germany
Titolo Testata:
NEURAL COMPUTATION
fascicolo: 8, volume: 13, anno: 2001,
pagine: 1811 - 1825
SICI:
0899-7667(200108)13:8<1811:DSCFRN>2.0.ZU;2-N
Fonte:
ISI
Lingua:
ENG
Soggetto:
MACAQUE STRIATE CORTEX; MODEL;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Life Sciences
Engineering, Computing & Technology
Citazioni:
24
Recensione:
Indirizzi per estratti:
Indirizzo: Wersing, H HONDA R&D Europe Germany, Carl Legien Str 30, D-63073 Offenbach, Germany HONDA R&D Europe Germany Carl Legien Str 30 Offenbach Germany D-63073
Citazione:
H. Wersing et al., "Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions", NEURAL COMP, 13(8), 2001, pp. 1811-1825

Abstract

We establish two conditions that ensure the nondivergence of additive recurrent networks with unsaturating piecewise linear transfer functions, also called linear threshold or semilinear transfer functions. As Hahnloser, Sarpeshkar, Mahowald, Douglas, and Seung (2000) showed, networks of this type can be efficiently built in silicon and exhibit the coexistence of digital selection and analog amplification in a single circuit. To obtain this behavior, the network must be multistable and nondivergent, and our conditions allow determining the regimes where this can be achieved with maximal recurrent amplification. The first condition can be applied to nonsymmetric networks and has a simple interpretation of requiring that the strength of local inhibition match the sum over excitatory weights converging onto a neuron. The second condition is restricted to symmetric networks, but can also take into account the stabilizing effect of nonlocal inhibitory interactions. We demonstrate the application of the conditions on a simple example and the orientation-selectivity mo del of Ben-Yishai, Lev Bar-Or, and Sompolinsky (1995). We show that the conditions can be used to identify in their model regions of maximal orientation-selective amplification and symmetry breaking.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 27/01/20 alle ore 07:15:16