BulDML at Institute of Mathematics and Informatics >
International Book Series Information Science and Computing >
2009 >
Book 09 Intelligent Processing >

Please use this identifier to cite or link to this item:

Title: The Cascade Neo-Fuzzy Architecture and its Online Learning Algorithm
Authors: Bodyanskiy, Yevgeniy
Viktorov, Yevgen
Keywords: Artificial Neural Networks
Constructive Approach
Fuzzy Inference
Hybrid Systems
Neo-Fuzzy Neuron
Real-Time Processing
Online Learning
Issue Date: 2009
Publisher: Institute of Information Theories and Applications FOI ITHEA
Abstract: In the paper learning algorithm for adjusting weight coefficients of the Cascade Neo-Fuzzy Neural Network (CNFNN) in sequential mode is introduced. Concerned architecture has the similar structure with the Cascade-Correlation Learning Architecture proposed by S.E. Fahlman and C. Lebiere, but differs from it in type of artificial neurons. CNFNN consists of neo-fuzzy neurons, which can be adjusted using high-speed linear learning procedures. Proposed CNFNN is characterized by high learning rate, low size of learning sample and its operations can be described by fuzzy linguistic “if-then” rules providing “transparency” of received results, as compared with conventional neural networks. Using of online learning algorithm allows to process input data sequentially in real time mode.
ISSN: 1313-0455
Appears in Collections:Book 09 Intelligent Processing

Files in This Item:

File Description SizeFormat
ibs-09-p14.pdf138.49 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0!   Creative Commons License