DocumentCode
288380
Title
A training approach based on linear separability analysis for layered perceptrons
Author
Zhang, D. ; Kamel, M. ; Elmasry, M.I.
Author_Institution
VLSI Res. Group, Waterloo Univ., Ont., Canada
Volume
1
fYear
1994
fDate
27 Jun-2 Jul 1994
Firstpage
517
Abstract
In this paper, we explore linear separability as a training approach for layered perceptrons. A training approach, called layer adaptation (LA), is presented. Its learning mechanism and implementation are described and examples are given to illustrate its effectiveness. Compared with the BP and the MRII algorithms, preliminary analysis shows that the LA is easily implemented using digital VLSI technology while the stability, the training time and the complexity in silicon are acceptable
Keywords
learning (artificial intelligence); multilayer perceptrons; neural nets; digital layered perceptrons; layer adaptation; learning mechanism; linear separability analysis; linear separable binary function; training time; Algorithm design and analysis; Artificial neural networks; Design engineering; Learning systems; Logic functions; Neurons; Stability analysis; System analysis and design; Systems engineering and theory; Very large scale integration;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location
Orlando, FL
Print_ISBN
0-7803-1901-X
Type
conf
DOI
10.1109/ICNN.1994.374217
Filename
374217
Link To Document