Hierarchical overlapped neural gas network with application to pattern classification

Neurocomputing

Volumn 35, Issue 1-4, 2000, Pages 165-176

  Atukorale, Ajantha S ^a   Suganthan, P N ^b  

^a UNIVERSITY OF QUEENSLAND   (Australia)

^b NANYANG TECHNOLOGICAL UNIVERSITY   (Singapore)

Author keywords

Character recognition; Hierarchical overlapped architecture; Multiple classifier fusion; Neural gas network; Self organizing maps

Indexed keywords

COMPUTATIONAL COMPLEXITY; COMPUTER ARCHITECTURE; LEARNING ALGORITHMS; OPTICAL CHARACTER RECOGNITION;

HIERARCHICAL OVERLAPPED NEURAL GAS (NG) NETWORKS; SELF-ORGANIZING MAPS (SOM);

NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; CLASSIFICATION; CONTROLLED STUDY; COST; GAS; HANDWRITING; MATHEMATICAL ANALYSIS; PRIORITY JOURNAL; SAMPLING; SYNAPSE; TIME; TRAINING; WEIGHT;

EID: 0034329472     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(00)00315-5     Document Type: Article

References (17)

1. Color image segmentation based on a neural gas network
2. Multiple network fusion using fuzzy logic
3. Fast sequential implementation of neural gas network for vector quantization
4. Self-organizing maps: Ordering, convergence properties and energy functions
5. Image reconstruction using improved neural gas
6. Design, collection and analysis of handwriting sample image databases
7. Off-line handwritten numeral recognition by perturbation method
8. An annealed neural gas network for robust vector quantization
9. Destructive fuzzy modeling using neural gas network
10. Combining classifiers: A Theoretical Framework
11. Neural gas network for vector quantization and its application to times-series prediction
12. A neural-gas network learns topologies
13. Hierarchical overlapped SOMs for pattern classification
14. Application of neural gas model in image compression
15. Handwritten digit recognition by neural gas model and population decoding