HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Wersing, H. Articles by Ritter, H. Search for Related Content PubMed PubMed Citation Articles by Wersing, H. Articles by Ritter, H.

Dynamical Stability Conditions for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions

Faculty of Technology, University of Bielefeld, D-33501 Bielefeld, Germany

Wolf-Jürgen Beyn

Faculty of Mathematics, University of Bielefeld, D-33501 Bielefeld, Germany

Helge Ritter

Faculty of Technology, University of Bielefeld, D-33501 Bielefeld, Germany

Correspondence: Current address: HONDA R&D Europe (Germany), Carl-Legien-Str.30, 63073 Offenbach/Main, Germany

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 model 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.

This article has been cited by other articles:

				K. Morita, M. Okada, and K. Aihara Selectivity and Stability via Dendritic Nonlinearity. Neural Comput., July 1, 2007; 19(7): 1798 - 1853. [Abstract] [Full Text] [PDF]

				H. J. Tang, K. C. Tan, and W. Zhang Analysis of Cyclic Dynamics for Networks of Linear Threshold Neurons Neural Comput., January 1, 2005; 17(1): 97 - 114. [Abstract] [Full Text] [PDF]

				R. H. R. Hahnloser, H. S. Seung, and J.-J. Slotine Permitted and Forbidden Sets in Symmetric Threshold-Linear Networks Neural Comput., March 1, 2003; 15(3): 621 - 638. [Abstract] [Full Text] [PDF]

				Z. Yi, K. K. Tan, and T. H. Lee Multistability Analysis for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions Neural Comput., March 1, 2003; 15(3): 639 - 662. [Abstract] [Full Text] [PDF]

				X. Xie, R. H. R. Hahnloser, and H. S. Seung Selectively Grouping Neurons in Recurrent Networks of Lateral Inhibition Neural Comput., November 1, 2002; 14(11): 2627 - 2646. [Abstract] [Full Text] [PDF]

				R. H. R. Hahnloser, R. J. Douglas, and K. Hepp Attentional Recruitment of Inter-Areal Recurrent Networks for Selective Gain Control Neural Comput., July 1, 2002; 14(7): 1669 - 1689. [Abstract] [Full Text] [PDF]