DocumentCode :
1902973
Title :
Meaning-based handling of don´t care attributes in artificial neural networks
Author :
Tschichold-Gurman, Nadine ; Dabija, Vlad G.
Author_Institution :
Inst. of Robotics, ETH Zurich, Switzerland
fYear :
1993
fDate :
1993
Firstpage :
281
Abstract :
An approach is presented for handling don´t care attribute values in artificial neural networks (ANNs), based on interpreting the meaning of the don´t care values in the context of the general meaning of the concepts learned by the network. The application of these ideas in the context of a particular ANN formalism (M-RCE networks) is discussed. Several considerations on using these ideas with other ANN formalisms are briefly presented
Keywords :
learning (artificial intelligence); neural nets; M-RCE networks; artificial neural networks; don´t care attributes; meaning-based handling; Accuracy; Artificial neural networks; Belts; Character recognition; Computational complexity; Data mining; Intelligent networks; Knowledge based systems; Pattern matching; Robots;
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.1993.298570
Filename :
298570
Link To Document :
بازگشت