DocumentCode
313622
Title
Knowledge-based fuzzy MLP with rough sets
Author
Banerjee, M. ; Mitra, Sushmita ; Pal, Sankar K.
Author_Institution
Machine Intelligence Unit, Indian Stat. Inst., Calcutta, India
Volume
1
fYear
1997
fDate
9-12 Jun 1997
Firstpage
499
Abstract
A new scheme of knowledge encoding using rough set-theoretic concepts is proposed. Knowledge collected from a data set is initially encoded among the connection weights of a fuzzy MLP. The network is then refined during training. Results on real data, demonstrate that the speed of learning and classification performance of the proposed scheme are better than that obtained with the fuzzy and conventional versions of the MLP (involving no initial knowledge)
Keywords
encoding; fuzzy neural nets; learning (artificial intelligence); multilayer perceptrons; pattern classification; set theory; speech recognition; classification performance; connection weights; knowledge encoding; knowledge-based fuzzy MLP; rough sets; speed of learning; training; Electronic mail; Encoding; Fuzzy neural networks; Fuzzy set theory; Fuzzy sets; Machine intelligence; Neural networks; Neurons; Rough sets; Uncertainty;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks,1997., International Conference on
Conference_Location
Houston, TX
Print_ISBN
0-7803-4122-8
Type
conf
DOI
10.1109/ICNN.1997.611719
Filename
611719
Link To Document