Title :
Winner-take-all discrete recurrent neural networks
Author :
Yi, Zhang ; Heng, Pheng-Ann ; Fung, Ping-Fu
Author_Institution :
Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, Shatin, China
fDate :
12/1/2000 12:00:00 AM
Abstract :
This paper proposes a discrete recurrent neural network has simple organizations and clear dynamic behaviors. The dynamic properties of the proposed winner-take-all networks are studied detail. Simulation results are given to show network performance. Since the network model is formulated as discrete time systems, it has advantages for computer simulations over digital simulations of a continuous time neural network model. Thus they can be easily implemented in digital hardware
Keywords :
discrete time systems; performance evaluation; recurrent neural nets; WTA networks; discrete time systems; dynamic properties; network model; network performance; network time response; winner-take-all discrete recurrent neural networks; Circuits; Convergence; Difference equations; Digital signal processing; Nonlinear equations; Polynomials; Recurrent neural networks; Signal processing algorithms; Transversal filters;
Journal_Title :
Circuits and Systems II: Analog and Digital Signal Processing, IEEE Transactions on
