DocumentCode :
1646816
Title :
Optimization of neural network weights and architectures for odor recognition using simulated annealing
Author :
Yamazaki, A. ; de Souto, M.C.P. ; Ludermir, T.B.
Author_Institution :
Center of Informatics, Univ. Fed. de Pernambuco, Recife, Brazil
Volume :
1
fYear :
2002
fDate :
6/24/1905 12:00:00 AM
Firstpage :
547
Lastpage :
552
Abstract :
Shows results of using simulated annealing for optimizing neural network architectures and weights. The algorithm generates networks with good generalization performance (mean classification error of 5.28%) and low complexity (mean number of connections of 11.68 out of 36) for an odor recognition task in an artificial nose
Keywords :
gas sensors; generalisation (artificial intelligence); multilayer perceptrons; neural net architecture; pattern classification; simulated annealing; artificial nose; generalization performance; low complexity; neural network architectures; neural network weights; odor recognition; simulated annealing; Artificial neural networks; Cooling; Costs; Informatics; Information processing; Neural networks; Nose; Optimization methods; Sensor arrays; Simulated annealing;
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.2002.1005531
Filename :
1005531
Link To Document :
بازگشت