Convergence theorem for kernel perceptron

ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age

Volumn 1, Issue , 2002, Pages 163-166

  Ikeda, K ^a  

^a KYOTO UNIVERSITY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ALGEBRA; ARTIFICIAL INTELLIGENCE; COMPUTATION THEORY; INFORMATION SCIENCE;

CONVERGENCE THEOREM; GENERAL LEARNING; KERNEL FUNCTION; KERNEL METHODS; LEARNING COEFFICIENTS; PERCEPTRON ALGORITHMS; PERCEPTRON LEARNING;

ALGORITHMS;

EID: 84965017495     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICONIP.2002.1202152     Document Type: Conference Paper

References (6)

1. T. Hanselmann and L. Noakes, Comparison between Support Vector Algorithm and Algebraic Perceptron, Proc. Int'l Joint Conf. Neural Networks (IJCNN), pp. 1459-1462, 2001.
2. T. Hanselmann and L. Noakes, Optimizing an Algebraic Perceptron Solution, Proc. Int'l Joint Conf. Neural Networks (IJCNN), pp. 1468-1473, 2001.
3. S. Haykin, Neural Networks - A Comprehensive Foundation, Prentice-Hall, 2nd ed., Upper Saddle River NJ, 1998.
4. K. Ikeda, Learning Curves of Polynomial Kernel Classifiers, in preparation.
5. F. Rosenblatt, The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain, Psychological Review, vol. 65, pp. 386-408, 1958.
6. V. N. Vapnik, Statistical Learning Theory, John Wiley and Sons, New York NY, 1998.