On the nonlinearity of pattern classifiers

Proceedings - International Conference on Pattern Recognition

Volumn 4, Issue , 1996, Pages 271-275

  Hoekstra, Aarnoud ^a   Duin, Robert P W ^a  

^a DELFT UNIVERSITY OF TECHNOLOGY   (Netherlands)

Author keywords

[No Author keywords available]

Indexed keywords

NEURAL NETWORKS;

CLASSIFICATION FUNCTIONS; GENERALIZATION CAPABILITY; K-NEAREST NEIGHBOURS; NEURAL CLASSIFIERS; NONLINEARITY MEASURES; PATTERN CLASSIFIER; QUADRATIC CLASSIFIERS;

PATTERN RECOGNITION;

EID: 0000092441     PISSN: 10514651     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICPR.1996.547429     Document Type: Conference Paper

References (7)

1. Demuth H. and Beale M. Neural Network toolbox for use with Marlab. The Math works Inc.. 1993.
2. Duin, R.P.W. Superlearning capabilities of neural networks ? In Proceedings of the 5th Scandinavian Conference on Image Analysis, pages 547-554. Norwegian Society for Image Processing and Pattern Recognition, May 25-28 1993.
3. Duin, R.P.W. PRTOOLS a Matlab toolbox for pattern recognition. Pattern Recognition group, Delft University of Technology, October 1995.
4. Funahashi, K-I. On the approximate realization of continuous mappings by neural networks. Neural Networks, 2: 183-192, 1989.
5. Hornik, K. Multilayer feed forward networks are universal approximators. Neural networks, 2:359-366, 1989.
6. Kanal, L.N. and Krishnaiah, P.R. Handbook ofstaristics 2: Classification pattern recognition and reduction of dimensionality. North-Holland, 1982.
7. Wolpert, D.H., editor. The matliematics of generalization. proceedings of the SFIKNLS workshop on formal approaches to supervised learning, Novemer 1994.