Prototype optimization for nearest-neighbor classification

Pattern Recognition

Volumn 35, Issue 6, 2002, Pages 1237-1245

  Huang, Y S ^a   Chiang, C C ^b   Shieh, J W ^c   Grimson, E ^d  

^a INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE   (Taiwan)

^b NATIONAL DONG HWA UNIVERSITY   (Taiwan)

^c YUAN ZE UNIVERSITY   (Taiwan)

^d MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Classification oriented error function; Competitive learning; Neural networks; Prototype construction; Prototype optimization

Indexed keywords

CLASSIFIERS; LEARNING SYSTEMS; NEURAL NETWORKS; OPTIMIZATION;

ERROR FUNCTIONS;

PATTERN RECOGNITION;

NEAREST NEIGHBOR ANALYSIS;

EID: 0036604873     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0031-3203(01)00124-8     Document Type: Article

References (10)

1. A new method of optimizing prototypes for nearest neighbor classifiers using a multi-layer network
2. The self-organization map
3. Finding prototypes for nearest-neighbor classifiers
4. An algorithm for a selective neighbor decision rule
5. Prototype optimization for nearest neighbor classifiers using a two-layer perception
6. A simulated annealing approach to construct optimized prototypes for nearest-neighbor classifiers
7. A deterministic annealing approach to clustering