Understanding stepwise generalization of Support Vector Machines: A toy model

Advances in Neural Information Processing Systems

Volumn , Issue , 2000, Pages 321-327

  Risau Gusman, Sebastian ^a   Gordon, Mirta B ^a  

^a CEA GRENOBLE   (France)

Author keywords

[No Author keywords available]

Indexed keywords

STATISTICAL MECHANICS;

INPUT DISTRIBUTIONS; LEARNING CURVES; PERCEPTRON; RELEVANT FEATURES; TOY MODELS;

SUPPORT VECTOR MACHINES;

EID: 84899010247     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. V. Vapnik (1995) The nature of statistical learning theory. Springer Verlag, New York.
2. R. Dietrich, M. Opper, and H. Sompolinsky (1999) Statistical Mechanics of Support Vector Networks. Phys. Rev. Lett. 82, 2975-2978.
3. A. Buhot and M. B. Gordon (1999) Statistical mechanics of support vector machines. ESANN'99-European Symposium on Artificial Neural Networks Proceedings, Michel Verleysen ed. 201-206
4. A. Buhot and M. B. Gordon (1998) Learning properties of support vector machines. Cond-Mat/9802179.
5. H. Yoon and J.-H. Oh (1998) Learning of higher order perceptrons with tunable complexities J. Phys. A: Math. Gen. 31, 7771-7784.
6. G. Gyorgyi and N. Tishby (1990) Statistical Theory of Learning a Rule. In Neural Networks and Spin Glasses (W. K. Theumann and R. Koberle, Worls Scientific), 3-36.
7. R. Meir (1995) Empirical risk minimizaton. A case study. Neural Comp. 7, 144-157.
8. C. Marangi, M. Biehl, S. A. Solla (1995) Supervised Learning from Clustered Examples Europhys. Lett. 30 (2), 117-122.