An improved self-organizing CPN-based fuzzy system with adaptive back-propagation algorithm

This paper describes an improved self-organizing CPN-based (Counter-Propagation Network) fuzzy system. Two self-organizing algorithms IUSOCPN and ISSOCPN, being unsupervised and supervised respectively, are introduced. The idea is to construct the neural-fuzzy system with a two-phase hybrid learning...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Fuzzy sets and systems Ročník 130; číslo 2; s. 227 - 236
Hlavní autori: Zhang, Zhiming, Wang, Yue, Tao, Ran, Zhou, Siyong
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Amsterdam Elsevier B.V 01.09.2002
Elsevier
Predmet:
Applied sciences
Artificial intelligence
Back-Propagation learning scheme
Biological and medical sciences
Circuit properties
Computer science; control theory; systems
Counterpropagation network
Digital circuits
Electric, optical and optoelectronic circuits
Electronic circuits
Electronics
Exact sciences and technology
Fundamental and applied biological sciences. Psychology
Fuzzy logic
General aspects
Gradient descent method
Learning and adaptive systems
Mathematical logic, foundations, set theory
Mathematics
Mathematics in biology. Statistical analysis. Models. Metrology. Data processing in biology (general aspects)
Neural network
Neuro-fuzzy systems
Sciences and techniques of general use
Self-Organization
Set theory
Fuzzy logic
Counterpropagation network
Self-Organization
Back-Propagation learning scheme
Neural network
Neuro-fuzzy systems
Gradient descent method
Learning
Backpropagation
Counter propagation network
Fuzzy system
Self organization
Scheme
Learning scheme
Neurofuzzy system
Gradient method
Multi-input multi-output system
ISSN:0165-0114, 1872-6801
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper describes an improved self-organizing CPN-based (Counter-Propagation Network) fuzzy system. Two self-organizing algorithms IUSOCPN and ISSOCPN, being unsupervised and supervised respectively, are introduced. The idea is to construct the neural-fuzzy system with a two-phase hybrid learning algorithm, which utilizes a CPN-based nearest-neighbor clustering scheme for both structure learning and initial parameters setting, and a gradient descent method with adaptive learning rate for fine tuning the parameters. The obtained network can be used in the same way as a CPN to model and control dynamic systems, while it has a faster learning speed than the original back-propagation algorithm. The comparative results on the examples suggest that the method is fairly efficient in terms of simple structure, fast learning speed, and relatively high modeling accuracy.
ISSN:0165-0114
1872-6801
DOI:10.1016/S0165-0114(01)00170-1