Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
NEURAL NETWORK TRAINING VIA QUADRATIC OPTIMIZATION Michael A. Satton' and PanosJ. Antsaklis2
 

Summary: NEURAL NETWORK TRAINING VIA QUADRATIC OPTIMIZATION
Michael A. Satton' and PanosJ. Antsaklis2
'Cardemcl Division -Code 1941
Naval SurfaceWarfaceCenter
Bethesda.Maryland 20084
Abstract - A new technique using quadratic optimization is proposed to find the
weights of a single neuron, or a single-layer neural network, and extended to the
multi-layer neural network. It is proposed here to fuui the weights for a neuron
by minimizing a cost function that is quadratic with respect to the neuron's
weights and to use these weights as an answer for minimizing a cost function
that is quadratic with respect to the neuron's outputs. Previous methods, such as
the least mean squares algorithm which is a grldient descent method and a
precursor of the back-propagation algorithm, iteratively find weights for the
neuron which minimiiz the eOst function directly involving the nonlinearity of
the neuron. By back-propagating the output error through the neural networks
layers, the proposed method is extended to the multi-layer neural network. The
described Quadratic Optimization Algorithm for the multi-layer neural network
mds to work best for classification problems and tends to achieve successful
results in a single iteration.
I INTRODUCTION

  

Source: Antsaklis, Panos - Department of Electrical Engineering, University of Notre Dame

 

Collections: Engineering