Share Email Print
cover

Proceedings Paper

Family of K-winner networks
Author(s): William J. Wolfe; Donald W. Mathis; C. Anderson; Jay Rothman; Michael Gottler; G. Brady; R. Walker; G. Duane; Gita Alaghband
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Mutually inhibitory networks are the fundamental building blocks of many complex systems. Despite their apparent simplicity they exhibit interesting behavior. We analyze a special class of such networks and provide parameters for reliable K-winner performance. We model the network dynamics using interactive activation and compare our results to the sigmoid model. When the external inputs are all equal we can derive network parameters that reliably select the units with the larger initial activations because the network converges to the nearest stable state. Conversely when the initial activations are all equal we can derive networks that reliably select the units with larger external inputs because the network converges to the lowest energy stable state. But when we mix initial activations with external inputs we get anomalous behavior. We analyze these discrepancies giving several examples. We also derive restrictions on initial states which ensure accurate K-winner performance when unequal external inputs are used. Much of this work was motivated by the K-winner networks described by Majani et at. in [1]. They use the sigmoid model and provide parameters for reliable K-winner performance. Their approach is based primarily on choosing an appropriate external input the same for all units that depends on K. We extend their work to the interactive activation model and analyze external inputs constant but possibly different for each unit more closely. Furthermore we observe a parametric duality in that changing

Paper Details

Date Published: 1 February 1991
PDF: 15 pages
Proc. SPIE 1382, Intelligent Robots and Computer Vision IX: Neural, Biological, and 3D Methods, (1 February 1991); doi: 10.1117/12.25216
Show Author Affiliations
William J. Wolfe, Univ. of Colorado/Denver (United States)
Donald W. Mathis, Univ. of Colorado/Denver (United States)
C. Anderson, Univ. of Colorado/Denver (United States)
Jay Rothman, Univ. of Colorado/Denver (United States)
Michael Gottler, Univ. of Colorado/Denver (United States)
G. Brady, Univ. of Colorado/Denver (United States)
R. Walker, Univ. of Colorado/Denver (United States)
G. Duane, Univ. of Colorado/Denver (United States)
Gita Alaghband, Univ. of Colorado/Denver (United States)


Published in SPIE Proceedings Vol. 1382:
Intelligent Robots and Computer Vision IX: Neural, Biological, and 3D Methods
David P. Casasent, Editor(s)

© SPIE. Terms of Use
Back to Top