DocumentCode :
1904971
Title :
Robustness of feedforward neural networks
Author :
Chiu, Ching-Tai ; Mehrotra, Kishan ; Mohan, Chilukuri K. ; Ranka, Sanjay
Author_Institution :
Sch. of Comput. & Inf. Sci., Syracuse Univ., NY, USA
fYear :
1993
fDate :
1993
Firstpage :
783
Abstract :
Methods are developed for measuring the sensitivity of links and nodes of a feedforward neural network, and for implementing a technique to ensure the development of neural networks that satisfy well-defined robustness criteria. Experimental observations indicate that performance degradation in the authors´ robust feedforward network is significantly less than a randomly trained feedforward network of the same size by an order of magnitude
Keywords :
feedforward neural nets; feedforward neural networks; link sensitivity measurement; node sensitivity; performance degradation; robustness criteria; Artificial neural networks; Backpropagation algorithms; Computer networks; Degradation; Fault tolerance; Feedforward neural networks; Mean square error methods; Neural networks; Robustness; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
Type :
conf
DOI :
10.1109/ICNN.1993.298655
Filename :
298655
Link To Document :
بازگشت