Comparison of neofuzzy and rough neural networks

Conventional neural network architectures generally lack semantics. Both rough and neofuzzy neurons introduce semantic structures in the conventional neural network models. Rough neurons make it possible to process data points with a range of values instead of a single precise value. Neofuzzy neuron...

Full description

Saved in:
Bibliographic Details
Published in:Information sciences 1998, Vol.110 (3), p.207-215
Main Author: Lingras, Pawan
Format: Article
Language:English
Subjects:
Fuzzy logic
Neofuzzy neurons
Neural networks
Rough neurons
Rough sets
Time series analysis
Traffic volume predictions
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Conventional neural network architectures generally lack semantics. Both rough and neofuzzy neurons introduce semantic structures in the conventional neural network models. Rough neurons make it possible to process data points with a range of values instead of a single precise value. Neofuzzy neurons make it possible to convert crisp values into fuzzy values. This paper compares rough and neofuzzy neural networks. Rough and neofuzzy neurons are demonstrated to be complementary to each other. It is shown that the introduction of rough and fuzzy semantic structures in neural networks can increase the accuracy of predictions.
ISSN:0020-0255
1872-6291
DOI:10.1016/S0020-0255(97)10045-7