On the K-winners-take-all-network
Advances in neural information processing systems 1
Clustering based on conditional distributions in an auxiliary space
Neural Computation
Recurrent network with large representational capacity
Neural Computation
Self-organizing neural projections
Neural Networks - 2006 Special issue: Advances in self-organizing maps--WSOM'05
An Inhibitory Neural-Network Circuit Exhibiting Noise Shaping with Subthreshold MOS Neuron Circuits
IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Computation with spikes in a winner-take-all network
Neural Computation
Computing the maximum using presynaptic inhibition with glutamate receptors
BVAI'07 Proceedings of the 2nd international conference on Advances in brain, vision and artificial intelligence
Dynamic analysis of a general class of winner-take-all competitive neural networks
IEEE Transactions on Neural Networks
A self-organized neural comparator
Neural Computation
| Hi-index | 0.00 |
The winner-take-all (WTA) property is essential to competitive-learning systems. This article discusses WTA-type neural networks composed of nonlinear dynamic model neurons, characterized by a nonlinear loss term. It is shown by mathematical analyses that these networks have the WTA property even when their neurons have nonidentical characteristics and the interconnections have nonidentical strengths. The class of WTA networks is further generalized to allow explicitly modeled interneurons between the principal cells. A model of a cyclically operating WTA system, capable of handling changing inputs by automatically inactivating the winner, is then set up and demonstrated by computer simulations.