Recursive training of neural networks for classification

Author

Aladjem, Mayer

Author_Institution

Dept. of Electr. & Comput. Eng., Ben-Gurion Univ. of the Negev, Beer-Sheva, Israel

Volume

11

Issue

2

fYear

2000

fDate

3/1/2000 12:00:00 AM

Firstpage

496

Lastpage

503

Abstract

A method for recursive training of neural networks for classification is proposed. It searches for the discriminant functions corresponding to several small local minima of the error function. The novelty of the proposed method lies in the transformation of the data into new training data with a deflated minimum of the error function and iteration to obtain the next solution. A simulation study and a character recognition application indicate that the proposed method has the potential to escape from local minima and to direct the local optimizer to new solutions

Keywords

learning (artificial intelligence); minimisation; neural nets; pattern classification; search problems; character recognition; classification; data transformation; deflated minimum; discriminant function search; error function local minima; iteration; local optimizer; neural networks; recursive training; Character recognition; Covariance matrix; Iterative algorithms; Linear discriminant analysis; Minimization methods; Neural networks; Nonhomogeneous media; Optimization methods; Robots; Training data;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.839018

Filename

839018