A Creating Method of Fuzzy Inference Rules by Self-Creating Neural Network
スポンサーリンク
概要
- 論文の詳細を見る
There are several fuzzy models using self-organization and vector quantization. It is well known that these models effectively construct fuzzy rules representing the distribution of input data, and are not affected even when the number of input dimensions increases. However most of these models are given the number of fuzzy rules in advance. In this paper, fuzzy rules are created sequentially so as to satisfy an objective value, and the proper number of them is determined finally. That is, the number of neurons which are reference vectors, is determined by using a self-creating neural network first. From the result, fuzzy rules are determined by using the descent method. Then if input-output data are approximated so as to satisfy the objective value, an algorithm terminates. Otherwise an algorithm for increasing the number of neurons is repeated. In order to show the validity of the proposed method, we performed some numerical examples.
- 日本知能情報ファジィ学会の論文
- 1999-06-15
著者
-
Fukumoto Shinya
Faculty Of Engineering Kagoshima University
-
KISHIDA Kazuya
Department of Electronic Control Engineering, Kagoshima National College of Technology
-
MIYAJIMA Hiromi
Faculty of Engineering, Kagoshima University
-
MIYAJIMA Hiromi
Department of Electrical and Electronics Engineering, Faculty of Engineering, Kagoshima University
-
Kishida K
Department Of Electronic Control Engineering Kagoshima National College Of Technology
-
Miyajima H
Department Of Electrical And Electronics Engineering Faculty Of Engineering Kagoshima University
-
Miyajima Hiromi
Faculty Of Engineering Kagoshima University
関連論文
- A Creating Method of Fuzzy Inference Rules by Self-Creating Neural Network
- An Investigation of Fuzzy Model Using AIC
- Constructive, Destructive and Simplified Learning Methods of Fuzzy Inference
- Learning Model in Relaxation Algorithm Influenced by Self-Organizing Maps for Image Restoration
- Numerical Evaluation of Incremental Vector Quantization Using Stochastic Relaxation(Nonlinear Theory and its Applications)
- A Hybrid Learning Approach to Self-Organizing Neural Network for Vector Quantization(Neuro, Fuzzy, GA)(Nonlinear Theory and its Applications)
- Shift-Invariant Associative Memory Based on Homogeneous Neural Networks(Nonlinear Theory and its Applications)
- Decision Procedure of Initial Values of Fuzzy Inference System Using Counterpropagation Networks
- Maximum Finding on One-Way Mesh-Connected Computers with Multiple Buses (Special Section of Papers Selected from ITC-CSCC'96)
- On Efficient Spare Arrangements and an Algorithm with Relocating Spares for Reconfiguring Processor Arrays (Special Section of Papers Selected from ITC-CSCC'96)
- On Methods for Reconfiguring Processor Arrays (Special Issue on Architectures, Algorithms and Networks for Massively parallel Computing)
- On Some Dynamical Properties of Threshold and Homogeneous Networks (Special Section on Nonlinear Theory and Its Applications)
- An Auto-Correlation Associative Memory which Has an Energy Function of Higher Order
- Competitive Learning Methods with Refractory and Creative Approaches (Special Section on Nonlinear Theory and Its Applications)
- Fuzzy Modeling in Some Reduction Methods of Inference Rules(Nonlinear Problems)(Regular Section)
- Construction Method of Fuzzy Inference by Rule Creation(Special Section on Papers Selected from ITC-CSCC 2002)
- State Sharing Methods in Statistical Fluctuation for Image Restoration(Nonlinear Theory and its Applications)