Performance analysis for a K-winners-take-all analog neural network: basic theory

Authors:
C. A. Marinov;B. D. Calvert
Affiliations:
Dept. of Electr. Eng., Polytech. Univ. of Bucharest, Romania;-
Venue:
IEEE Transactions on Neural Networks
Year:
2003

Citing 0
Cited 9

2008 Special Issue: Two k-winners-take-all networks with discontinuous activation functions

Neural Networks
A Discrete-Time Recurrent Neural Network with One Neuron for k-Winners-Take-All Operation

ISNN '09 Proceedings of the 6th International Symposium on Neural Networks on Advances in Neural Networks
A discrete-time dynamic K-winners-take-all neural circuit

Neurocomputing
A new recurrent neural network for solving convex quadratic programming problems with an application to the k-winners-take-all problem

IEEE Transactions on Neural Networks
A winner-take-all circuit using neural networks as building blocks

Neurocomputing
Time-oriented synthesis for a WTA continuous-time neural network affected by capacitive cross-coupling

IEEE Transactions on Circuits and Systems Part I: Regular Papers
Analysis and design of a k-winners-take-all model with a single state variable and the heaviside step activation function

IEEE Transactions on Neural Networks
Parametric sensitivity and scalability of k-winners-take-all networks with a single state variable and infinity-gain activation functions

ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part I
A model of analogue K-winners-take-all neural circuit

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In a previous work, the authors proposed an analog Hopfield-type neural network that identified the K largest components of a list of real numbers. In this work, we identify computable restrictions on the parameters, in order that the network can repeatedly process lists, one after the other, at a given rate. A complete mathematical analysis gives analytical bounds for the time required in terms of circuit parameters, the length of the lists, and the relative separation of list elements. This allows practical setting of circuit parameters for required clocking times. The emphasis is on high gain functioning of each neuron. Numerical investigations show the accuracy of the theoretical predictions, and study the influence of various parameters on performance.