DocumentCode
2618659
Title
Feedforward Bayesian neural network and continuous attributes
Author
Kononenko, Igor
Author_Institution
Fac. of Electr. & Comput. Eng., Ljubljana Univ.
fYear
1991
fDate
18-21 Nov 1991
Firstpage
146
Abstract
Two methods for dealing with continuous attributes are proposed. The fuzzy learning method assumes fuzzy bounds of a continuous attribute during learning and the fuzzy classification method assumes fuzzy bounds during classification. The performance was tested on two medical diagnostic problems. The results obtained show that the proposed methods for dealing with continuous attributes perform better than the splitting of the attribute´s values with exact bounds
Keywords
fuzzy logic; fuzzy set theory; learning systems; neural nets; pattern recognition; continuous attributes; feedforward Bayesian neural network; fuzzy bounds; fuzzy classification; fuzzy learning method; fuzzy logic; fuzzy set theory; medical diagnostic problems; pattern recognition; Backpropagation algorithms; Bayesian methods; Classification tree analysis; Computer networks; Feedforward neural networks; Learning systems; Machine learning algorithms; Medical diagnosis; Neural networks; Robustness;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN
0-7803-0227-3
Type
conf
DOI
10.1109/IJCNN.1991.170395
Filename
170395
Link To Document