Title :
A distance based network for sequence processing
Author :
Calvert, D. ; Stacey, D.A. ; Kamel, M.S.
Author_Institution :
Dept. of Comput. & Inf. Sci., Guelph Univ., Ont., Canada
Abstract :
This work describes the development of an artificial neural network for sequence modeling and recall. The system described learns an initial data set and treats that as an exemplar for all later comparisons. One of the principles of this work was to design a system that takes advantage of the architectural features common to neural networks. These features are many simple storage locations (weights) and a collection of simple processing elements
Keywords :
ART neural nets; feature extraction; learning (artificial intelligence); pattern recognition; self-organising feature maps; sequences; ART networks; SOM; adaptive resonance theory networks; distance based network; neural network architectural features; processing elements; self-organizing map; sequence modeling; sequence processing; sequence recall; storage locations; weights; Artificial neural networks; Helium; Information science; Intelligent networks; Neural networks; Subspace constraints; Testing; Time measurement; Training data;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.687256
