Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

A new algorithm for learning in piecewise-linear neural networks E.F. Gada,*, A.F. Atiyab

Summary: A new algorithm for learning in piecewise-linear neural networks
E.F. Gada,*, A.F. Atiyab
, S. Shaheenc
, A. El-Dessoukid
Department of Electrical Engineering, Carleton University, 1125 Colonel By Drive, Ottawa, Ont., Canada K15 5B6
Department of Electrical Engineering, Caltech 136-93 Pasadena, CA 91125, USA
Department of Computer Engineering, Cairo University, Giza, Egypt
Informatics Research Institute, MCSRTA, Alexandria, Egypt
Received 27 June 1997; revised 15 March 2000; accepted 15 March 2000
Piecewise-linear (PWL) neural networks are widely known for their amenability to digital implementation. This paper presents a new
algorithm for learning in PWL networks consisting of a single hidden layer. The approach adopted is based upon constructing a continuous
PWL error function and developing an efficient algorithm to minimize it. The algorithm consists of two basic stages in searching the weight
space. The first stage of the optimization algorithm is used to locate a point in the weight space representing the intersection of N linearly
independent hyperplanes, with N being the number of weights in the network. The second stage is then called to use this point as a starting
point in order to continue searching by moving along the single-dimension boundaries between the different linear regions of the error


Source: Abu-Mostafa, Yaser S. - Department of Mechanical Engineering & Computer Science Department, California Institute of Technology


Collections: Computer Technologies and Information Sciences