DocumentCode :
288388
Title :
Are modified back-propagation algorithms worth the effort?
Author :
Alpsan, D. ; Towsey, M. ; Ozdamar, Ozcan ; Tsoi, A. ; Ghista, D.N.
Author_Institution :
Dept. of Med. Phys. & Eng., United Arab Emirates Univ., Al-Ain, United Arab Emirates
Volume :
1
fYear :
1994
fDate :
27 Jun-2 Jul 1994
Firstpage :
567
Abstract :
A wide range of modifications and extensions to the backpropagation (BP) algorithm have been tested on a real world medical problem. Our results show that: 1) proper tuning of learning parameters of standard BP not only increases the speed of learning but also has a significant effect on generalisation; 2) parameter combinations and training options which lead to fast learning do not usually yield good generalisation and vice versa; 3) standard BP may be fast enough when its parameters are finely tuned; 4) modifications developed on artificial problems for faster learning do not necessarily give faster learning on real-world problems, and when they do, it may be at the expense of generalisation; and 5) even when modified BP algorithms perform well, they may require extensive fine-tuning to achieve this performance. For our problem, none of the modifications could justify the effort to implement them
Keywords :
backpropagation; medical computing; neural nets; tuning; backpropagation; generalisation; learning parameters; learning speed; medical computing; neural networks; real-world problems; tuning; Artificial neural networks; Backpropagation algorithms; Biological neural networks; Biomedical engineering; Feedforward neural networks; Logistics; Medical tests; Neural networks; Physics; Standards development;
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.1994.374227
Filename :
374227
Link To Document :
بازگشت