Title :
Configuration selection for two-layer memory network pattern classifiers
Author :
Fairhurst, Michael C. ; Mattoso Maia, M.
Author_Institution :
University of Kent at Canterbury, Electronics Laboratories, Canterbury, UK
Abstract :
Appropriate allocation of decision-making tasks between processing levels in a hierarchical memory network pattern classifier can enhance efficient utilisation of resources and reduce implementation complexity. The letter describes and compares two strategies for such resource allocation, with specific reference to decision refinement between processing levels.
Keywords :
decision theory; pattern recognition; configuration selection; decision-making tasks; pattern recognition; processing levels; resource allocation; two-layer memory network pattern classifiers;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19850680