DocumentCode :
2712057
Title :
Bidirectional Associative Memories, Self-Organizing Maps and k-Winners-Take-All: Uniting feature extraction and topological principles
Author :
Chartier, Sylvain ; Giguère, Gyslain ; Langlois, Dominic ; Sioufi, Rana
Author_Institution :
Sch. of Psychol., Univ. of Ottawa, Ottawa, ON, Canada
fYear :
2009
fDate :
14-19 June 2009
Firstpage :
503
Lastpage :
510
Abstract :
In this paper, we introduce a network combining k-Winners-Take-All and Self-Organizing Map principles within a Feature Extracting Bidirectional Associative Memory. When compared with its ldquostrictly winner-take-allrdquo version, the modified model shows increased performance for clustering, by producing a better weight distribution and a lower dispersion level (higher density) for each given category. Moreover, because the model is recurrent, it is able to develop prototype representations strictly from exemplar encounters. Finally, just like any recurrent associative memory, the model keeps its reconstructive memory and noise filtering properties.
Keywords :
content-addressable storage; feature extraction; self-organising feature maps; topology; bidirectional associative memory; feature extraction; k-winners-take-all; noise filtering property; reconstructive memory; recurrent associative memory; self-organizing maps; topological principles; weight distribution; Associative memory; Clustering algorithms; Feature extraction; Independent component analysis; Magnesium compounds; Neural networks; Principal component analysis; Prototypes; Psychology; Self organizing feature maps;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2009. IJCNN 2009. International Joint Conference on
Conference_Location :
Atlanta, GA
ISSN :
1098-7576
Print_ISBN :
978-1-4244-3548-7
Electronic_ISBN :
1098-7576
Type :
conf
DOI :
10.1109/IJCNN.2009.5178923
Filename :
5178923
Link To Document :
بازگشت