Share Email Print

Proceedings Paper

Relabeling exchange method (REM) for learning in neural networks
Author(s): Wen Wu; Richard J. Mammone
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The supervised training of neural networks require the use of output labels which are usually arbitrarily assigned. In this paper it is shown that there is a significant difference in the rms error of learning when `optimal' label assignment schemes are used. We have investigated two efficient random search algorithms to solve the relabeling problem: the simulated annealing and the genetic algorithm. However, we found them to be computationally expensive. Therefore we shall introduce a new heuristic algorithm called the Relabeling Exchange Method (REM) which is computationally more attractive and produces optimal performance. REM has been used to organize the optimal structure for multi-layered perceptrons and neural tree networks. The method is a general one and can be implemented as a modification to standard training algorithms. The motivation of the new relabeling strategy is based on the present interpretation of dyslexia as an encoding problem.

Paper Details

Date Published: 1 February 1994
PDF: 10 pages
Proc. SPIE 2093, Substance Identification Analytics, (1 February 1994); doi: 10.1117/12.172505
Show Author Affiliations
Wen Wu, Rutgers Univ. (United States)
Richard J. Mammone, Rutgers Univ. (United States)

Published in SPIE Proceedings Vol. 2093:
Substance Identification Analytics
James L. Flanagan; Richard J. Mammone; Albert E. Brandenstein; Edward Roy Pike M.D.; Stelios C. A. Thomopoulos; Marie-Paule Boyer; H. K. Huang; Osman M. Ratib, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?