Title :
Convergence Time of Wang´s kWTA Network with Stochastic Output Nodes
Author :
Ho, K.I.J. ; Wei-Bin Lee ; Siu-Chung Lau ; Sum, John
Author_Institution :
Dept. of Comp. Sci. & Comm. Eng., Providence Univ., Sha-Lu, Taiwan
Abstract :
Recently, an extended Wang´s kWTA network with stochastic output nodes has been studied. It is shown that this extended model converges asymptotically. In this paper, we further studies the convergence time of this model. The convergence time is defined as the time taken for the model to reach a finite region around the convergent. With this definition, an approximation of convergence time is derived and its viability is shown by simulation results.
Keywords :
approximation theory; convergence of numerical methods; network theory (graphs); neural nets; Wang WTA network; asymptotic convergence time; convergence time approximation; extended model; stochastic output nodes; Biological neural networks; Convergence; Educational institutions; Fault tolerance; Hardware; Simulation; Stochastic processes; Convergence Analysis; Convergence Time; Dual Neural Networks; Stochastic Output Nodes; kWTA;
Conference_Titel :
Mobile, Ubiquitous, and Intelligent Computing (MUSIC), 2012 Third FTRA International Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
978-1-4673-1956-0
DOI :
10.1109/MUSIC.2012.39
