New bounds for correct generalization

Author

Mattera, Davide ; Palmieri, Francesco

Author_Institution

Dipartimento di Ingegneria Elettronica, Naples Univ., Italy

Volume

2

fYear

1997

fDate

9-12 Jun 1997

Firstpage

1051

Abstract

A theoretical approach to the determination of the number of training examples for a neural network architecture is provided by the theory of Vapnik and Chervonenkis on the minimization of the empirical risk. We report here a new bound on the joint probability that both the approximation error between the binary function learned by the input/output examples and the target binary function is larger than ε and the empirical error on the examples is smaller than a fixed non-null fraction of ε. The given bounds are independent of the probability distribution on the input space and improve some existing results on the generalization abilities of an adaptive binary function

Keywords

error statistics; generalisation (artificial intelligence); learning (artificial intelligence); minimisation; neural net architecture; probability; Vapnik-Chervonenkis theory; approximation error; binary function; bounds; empirical risk; error probability; generalization; minimization; neural network architecture; probability; Error correction; Error probability; Frequency measurement; Neural networks; Probability distribution; Risk analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks,1997., International Conference on

Conference_Location

Houston, TX

Print_ISBN

0-7803-4122-8

Type

conf

DOI

10.1109/ICNN.1997.616173

Filename

616173