Title :
K-winner networks
Author :
Wolfe, W.J. ; Mathis, D. ; Anderson, C. ; Rothman, J. ; Gottler, M. ; Brady, G. ; Walker, R. ; Duane, G. ; Alaghband, G.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Colorado Univ., Denver, CO, USA
fDate :
3/1/1991 12:00:00 AM
Abstract :
A special class of mutually inhibitory networks is analyzed, and parameters for reliable K-winner performance are presented. The network dynamics are modeled using interactive activation, and results are compared with the sigmoid model. For equal external inputs, network parameters that select the units with the larger initial activations (the network converges to the nearest stable state) are derived. Conversely, for equal initial activations, networks that select the units with larger external inputs (the network converges to the lowest energy stable state) are derived. When initial activations are mixed with external inputs, anomalous behavior results. These discrepancies are analyzed with several examples. Restrictions on initial states are derived which ensure accurate K-winner performance when unequal external inputs are used
Keywords :
neural nets; K-winner networks; interactive activation; mutually inhibitory networks; network dynamics; neural nets; Associative memory; Cause effect analysis; Differential equations; Hypercubes; Linear systems; Performance analysis; Solid modeling; Stability analysis; Symmetric matrices; Vectors;
Journal_Title :
Neural Networks, IEEE Transactions on