Understanding Stepwise Generalization of Support Vector Machines: a Toy Model.

RISAU GUSMAN, SEBASTIAN; GORDON, MIRTA B.

Denver (EE. UU.)

Congreso; Neural Information Processing Systems 12; 1999

Neural Information Processing Systems Foundation

In this article we study the effects of introducing structure in the input distribution of the data to be learnt by a simple perceptron. We determine the learning curves within the framework of Statistical Mechanics. Stepwise generalization occurs as a function of the number of examples when the distribution of patterns is highly anisotropic. Although extremely simple, the model seems to capture the relevant features of a class of Support Vector Machines which was recently shown to present this behavior.