Improving RBF-DDA performance on optical character recognition through parameter selection

Proceedings - International Conference on Pattern Recognition

Volumn 4, Issue , 2004, Pages 625-628

  Oliveira, A L I ^a   Neto, F B L ^a   Meira, S R L ^b  

^a FEDERAL UNIVERSITY OF PERNAMBUCO   (Brazil)

^b FEDERAL UNIVERSITY OF PERNAMBUCO   (Brazil)

Author keywords

[No Author keywords available]

Indexed keywords

DATASETS; DYNAMIC DECAY ADJUSTMENT (DDA); MULTI-LAYER PERCEPTRONS (MLP); TRAINING ALGORITHMS;

ALGORITHMS; DATABASE SYSTEMS; ERROR ANALYSIS; MATHEMATICAL MODELS; NEURAL NETWORKS; PARAMETER ESTIMATION; PROBLEM SOLVING;

OPTICAL CHARACTER RECOGNITION;

EID: 10044280170     PISSN: 10514651     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICPR.2004.1333850     Document Type: Conference Paper

References (6)

1. M. Berthold and J. Diamond. Constructive training of probabilistic neural networks. Neurocomputing, 19:167-183, 1998.
2. M. R. Berthold and J. Diamond. Boosting the performance of RBF networks with dynamic decay adjustment. In G. T. et al, editor, Advances in Neural Information Processing, volume 7. 1995.
3. C. Blake and C. Merz. UCI repository of machine learning databases. Available from [http://www.ics.uci.edu/mlearn/MLRepository.html], 1998.
4. P. W. Frey and D. J. Slate. Letter recognition using holland-style adaptive classifiers. Machine Learning, 6(2), mar 1991.
5. C. Kaynak and E. Alpaydin. Multistage cascading of multiple classifiers: One man's noise in another man's data. In Proc. of the 17th International Conference on Machine Learning, 2000.
6. S. Kumar, J. Ghosh, and M. Crawford. A bayesian pairwise classifier for character recognition. In N. Mursheed, editor, Cognitive and Neural Models for Word Recognition and Document Processing. World Scientific Press, 2000.