Snap-drift self organising map

Authors:
Dominic Palmer-Brown;Chrisina Draganova
Affiliations:
London Metropolitan University, Faculty of Computing, London, UK;London Metropolitan University, Faculty of Computing, London, UK
Venue:
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
Year:
2010

Citing 5
Cited 0

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
A Probabilistic Classification System for Predicting the Cellular Localization Sites of Proteins

Proceedings of the Fourth International Conference on Intelligent Systems for Molecular Biology
Extracting road information from recorded GPS data using snap-drift neural network

Neurocomputing
Snap-drift neural network for selecting student feedback

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Phonetic feature discovery in speech using snap-drift learning

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel self-organising map (SOM) algorithm based on the snapdrift neural network (SDSOM) is proposed. The modal learning algorithm deploys a combination of the snap-drift modes; fuzzy AND (or Min) learning (snap), and Learning Vector Quantisation (drift). The performance of the algorithm is tested on several well known data sets and compared with the traditional Kohonen SOM algorithm. It is found that the snap mode makes the learning in SDSOM faster than the Kohonen SOM, and that it leads to the formation of more compact maps. When using the maps for classification, SDSOM gives better performance, based on labelled winning nodes, than Kohonen SOM on a variety of data sets.