Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions

Wersing H, Beyn W-J, Ritter H (2001)
Neural Computation 13(8): 1811-1825.

Zeitschriftenaufsatz | Veröffentlicht| Englisch
 
Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Abstract / Bemerkung
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.
Erscheinungsjahr
2001
Zeitschriftentitel
Neural Computation
Band
13
Ausgabe
8
Seite(n)
1811-1825
ISSN
0899-7667
Page URI
https://pub.uni-bielefeld.de/record/1616820

Zitieren

Wersing H, Beyn W-J, Ritter H. Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions. Neural Computation. 2001;13(8):1811-1825.
Wersing, H., Beyn, W. - J., & Ritter, H. (2001). Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions. Neural Computation, 13(8), 1811-1825. doi:10.1162/08997660152469350
Wersing, H., Beyn, W. - J., and Ritter, H. (2001). Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions. Neural Computation 13, 1811-1825.
Wersing, H., Beyn, W.-J., & Ritter, H., 2001. Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions. Neural Computation, 13(8), p 1811-1825.
H. Wersing, W.-J. Beyn, and H. Ritter, “Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions”, Neural Computation, vol. 13, 2001, pp. 1811-1825.
Wersing, H., Beyn, W.-J., Ritter, H.: Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions. Neural Computation. 13, 1811-1825 (2001).
Wersing, Heiko, Beyn, Wolf-Jürgen, and Ritter, Helge. “Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions”. Neural Computation 13.8 (2001): 1811-1825.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Quellen

PMID: 11506671
PubMed | Europe PMC

Suchen in

Google Scholar