Limited precision incremental communication: error analysis

The effects of the limited precision incremental communication method on the convergence behavior and performance degradation of multilayer perceptrons are investigated. The nonlinear effects of representing the incremental values with reduced (limited) precision on the commonly used error backpropa...

Full description

Saved in:
Bibliographic Details
Published inProceedings of International Conference on Neural Networks (ICNN'96) Vol. 2; pp. 1127 - 1132 vol.2
Main Authors Ghorbani, A.A., Bhavsar, V.C.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1996
Subjects
Analytical models
Artificial neural networks
Backpropagation algorithms
Computer science
Convergence
Degradation
Error analysis
Logistics
Multilayer perceptrons
Nonhomogeneous media
Online AccessGet full text

Cover

More Information
Summary:The effects of the limited precision incremental communication method on the convergence behavior and performance degradation of multilayer perceptrons are investigated. The nonlinear effects of representing the incremental values with reduced (limited) precision on the commonly used error backpropagation training algorithm are analysed. It is shown that the small perturbation in the input(s)/output of a node does not enforce instability. However, when the precision of the incremental values falls below a certain level, the network fails to converge. The analysis is supported by simulation studies of two learning problems.
ISBN:0780332105
9780780332102
DOI:10.1109/ICNN.1996.549056