Paper
29 October 1993 Global dynamics of winner-take-all networks
Ibrahim M. Elfadel
Author Affiliations +
Abstract
In this paper, we study the global dynamics of winner-take-all (WTA) networks. These networks generalize Hopfield's networks to the case where competitive behavior is enforced within clusters of neurons while the interaction between clusters is modeled by cluster-to- cluster connectivity matrices. Under the assumption of intracluster and intercluster symmetric connectivity, we show the existence of Lyapunov functions that allow us to draw rigorous results about the long-term behavior for both the iterated-map and continuous-time dynamics of the WTA network. Specifically, we show that the attractors of the synchronous, iterated- map dynamics are either fixed points or limit cycles of period 2. Moreover, if the network connectivity matrix satisfies a weakened form of positive definiteness, limit cycles can be ruled out. Furthermore, we show that the attractors of the continuous-time dynamics are only fixed points for any connectivity matrix. Finally, we generalize the WTA dynamics to distributed networks of clustered neurons where the only requirement is that the input-output mapping of each cluster be the gradient map of a convex potential.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ibrahim M. Elfadel "Global dynamics of winner-take-all networks", Proc. SPIE 2032, Neural and Stochastic Methods in Image and Signal Processing II, (29 October 1993); https://doi.org/10.1117/12.162029
Lens.org Logo
CITATIONS
Cited by 5 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Analog electronics

Fourier transforms

Dynamical systems

Binary data

Neurons

Brain mapping

Matrices

RELATED CONTENT

Pattern Recognition Using A Neural Network
Proceedings of SPIE (February 19 1988)
3D well-composed pictures
Proceedings of SPIE (August 11 1995)
Techniques for high-performance analog neural networks
Proceedings of SPIE (March 01 1992)
VLSI implementable parallel stochastic learning algorithm
Proceedings of SPIE (August 11 1995)
New Algorithms For Automated Symmetry Recognition
Proceedings of SPIE (February 19 1988)
Ho-Kashyap CAAP 1:1 associative processors
Proceedings of SPIE (February 01 1991)

Back to Top