Reference : Evolutionary fuzzy system for architecture control in a constructive neural network
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/10993/36485
Evolutionary fuzzy system for architecture control in a constructive neural network
English
Calvo, R. [> >]
Figueiredo, M. [> >]
Antonelo, Eric Aislan mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) >]
2005
2005 International Symposium on Computational Intelligence in Robotics and Automation
IEEE
541-546
Yes
International
International Symposium on Computational Intelligence in Robotics and Automation
27-06-2005 to 30-06-2005
[en] mobile robots ; fuzzy neural nets ; evolutionary computation; navigation;evolutionary fuzzy system;architecture control;constructive neural network;autonomous navigation;classifier system;Takagi-Sugeno fuzzy rules;mobile robot;evolutionary learning;classifier fuzzy system;classifier systems;robot navigation;Fuzzy systems;Control systems;Neural networks;Navigation;Takagi-Sugeno model;Fuzzy control;Fuzzy neural networks;Mobile robots;Learning systems;Neurons;constructive neural networks;classifier systems;robot navigation
[en] This work describes an evolutionary system to control the growth of a constructive neural network for autonomous navigation. A classifier system generates Takagi-Sugeno fuzzy rules and controls the architecture of a constructive neural network. The performance of the mobile robot guides the evolutionary learning mechanism. Experiments show the efficiency of the classifier fuzzy system for analyzing if it is worth inserting a new neuron into the architecture.
http://hdl.handle.net/10993/36485
10.1109/CIRA.2005.1554333
https://ieeexplore.ieee.org/abstract/document/1554333/

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
2005_calvo_cira.pdfAuthor postprint117.01 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.