Competitive learning algorithms for vector quantization
Neural Networks
Self-organizing maps
Competitively Inhibited Neural Networks for Adaptive Parameter Estimation
Competitively Inhibited Neural Networks for Adaptive Parameter Estimation
Winner-take-all neural networks using the highest threshold
IEEE Transactions on Neural Networks
Centroid neural network for unsupervised competitive learning
IEEE Transactions on Neural Networks
Dynamic Growing Self-organizing Neural Network for Clustering
ADMA '08 Proceedings of the 4th international conference on Advanced Data Mining and Applications
Hi-index | 0.00 |
In generalised lotto-type competitive learning algorithm more than one winner exist. The winners are divided into a number of tiers (or divisions), with each tier being rewarded differently. All the losers are penalised (which can be equally or differently). In order to study the various properties of the generalised lotto-type competitive learning, a set of equations, which governs its operations, is formulated. This is then used to analyse the stability and other dynamic properties of the generalised lotto-type competitive learning.