DocumentCode
1679841
Title
Pair attribute learning: network construction using pair features
Author
Henderson, Eric K. ; Martinez, Tony R.
Author_Institution
Cambridge Univ., UK
Volume
3
fYear
2002
fDate
6/24/1905 12:00:00 AM
Firstpage
2556
Lastpage
2561
Abstract
We present the pair attribute learning (PAL) algorithm for the selection of relevant inputs and network topology. Correlations on training instance pairs are used to drive network construction of a single-hidden layer MLP. Results on nine learning problems demonstrate 70% less complexity, on average, without a significant loss of accuracy
Keywords
learning (artificial intelligence); multilayer perceptrons; pattern classification; learning problems; network construction; network topology; pair attribute learning algorithm; pair features; single-hidden layer MLP; Accuracy; Application software; Backpropagation algorithms; Computer science; Iterative algorithms; Iterative methods; Network topology; Neural networks; Predictive maintenance; Training data;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location
Honolulu, HI
ISSN
1098-7576
Print_ISBN
0-7803-7278-6
Type
conf
DOI
10.1109/IJCNN.2002.1007546
Filename
1007546
Link To Document