Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Recursive Training of Neural Networks for Pattern Recognition Mayer Aladjem
 

Summary: Recursive Training of Neural Networks for Pattern Recognition
Mayer Aladjem
Department of Electrical and Computer Engineering
Ben­Gurion University of the Negev
P.O.B. 653, 84105 Beer­Sheva, Israel
aladjem@ee.bgu.ac.il
Abstract
In this paper we discuss our method for recursive
training of neural networks for classification. 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 er­
ror 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 es­
cape from local minima and to direct the local optimizer
to new solutions.
Index Terms---Networks for classification, linear and
non­linear classification functions, projection pursuit.

  

Source: Aladjem, Mayer - Department of Electrical and Computer Engineering, Ben-Gurion University

 

Collections: Computer Technologies and Information Sciences