Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
An Incremental Neural Network Construction Algorithm for Training Multilayer Perceptrons
 

Summary: An Incremental Neural Network Construction
Algorithm for Training Multilayer Perceptrons
Oya Aran, Ethem Alpaydin
Department of Computer Engineering,
Bogazic¸i University TR-34342
Istanbul, Turkey
aranoya, alpaydin¡@boun.edu.tr
Abstract-- The problem of determining the architecture of a
multilayer perceptron together with the disadvantages of the stan-
dard backpropagation algorithm, directed the research towards
algorithms that determine not only the weights but also the struc-
ture of the network necessary for learning the data. We propose a
Constructive Algorithm with Multiple Operators using Statistical
Test (MOST) for determining the architecture. The networks that
are constructed by MOST can have multiple hidden layers with
multiple hidden units in each layer. The algorithm uses node re-
moval, addition and layer addition and determines the number of
nodes in layers by heuristics. It applies a statistical test to com-
pare different architectures. The results are promising and near
optimal.

  

Source: Alpaydın, Ethem - Department of Computer Engineering, Bogaziçi University

 

Collections: Computer Technologies and Information Sciences