Title of article
Generalization and learning error for nonlinear perceptron
Author/Authors
I. Butiter and N. Shcherbina ، نويسنده , , M. and Tirozzi، نويسنده , , B.، نويسنده ,
Issue Information
روزنامه با شماره پیاپی سال 2002
Pages
13
From page
259
To page
271
Abstract
A rigorous derivation of the asymptotic behaviour of learning and prediction error for the nonlinear perceptron is presented. The saddle-point method is used for evaluating these quantities.
Keywords
perceptron , Saddle point , Learning , Law large numbers
Journal title
Mathematical and Computer Modelling
Serial Year
2002
Journal title
Mathematical and Computer Modelling
Record number
1592334
Link To Document