Title :
An improved maxnet
Author :
Chang, Yi C. ; Yu, Sung-Nien ; Kuo, Chung J.
Author_Institution :
Dept. of Electr. Eng., Nat. Chung Cheng Univ., Taipei, Taiwan
Abstract :
In the proposed model, dynamic inhibitory weights are used to speed up the convergence rate, and a new convergence rule is applied to find all maxima. The hardware implementation of the proposed model is presented in the study, and simulation results indicate that the proposed model converges much faster than the other networks.
Keywords :
convergence; neural nets; set theory; Maxnet model; convergence rate; dynamic inhibitory weight; winner-take-all network; Acceleration; Computational complexity; Convergence; Hardware; Limiting; Logic; Pattern recognition; Research and development; Signal processing; Signal processing algorithms; Convergence rate; inhibitory weights; winner-take-all network; Algorithms; Computer Simulation; Feedback; Models, Statistical; Neural Networks (Computer); Pattern Recognition, Automated; Signal Processing, Computer-Assisted;
Journal_Title :
Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on
DOI :
10.1109/TSMCB.2004.834420
