DocumentCode :
2312393
Title :
A priori information in network design
Author :
Dimopoulos, K.P. ; Kambhampati, C.
Author_Institution :
Reading Univ., UK
Volume :
1
fYear :
1998
fDate :
1-4 Sep 1998
Firstpage :
715
Abstract :
An analysis of how a priori knowledge of relative order can be applied to train a neural network effectively, is presented. In many cases only an approximate model of a system is known. The information from this model can be used to produce a more accurate one. Often this knowledge is not available or at best is inaccurate. Under these conditions, the relative order can be determined from the structure of the trained network using the rules developed here. This analysis is demonstrated with two examples
Keywords :
learning (artificial intelligence); a priori information; network design; relative order;
fLanguage :
English
Publisher :
iet
Conference_Titel :
Control '98. UKACC International Conference on (Conf. Publ. No. 455)
Conference_Location :
Swansea
ISSN :
0537-9989
Print_ISBN :
0-85296-708-X
Type :
conf
DOI :
10.1049/cp:19980317
Filename :
728023
Link To Document :
بازگشت