http://swrc.ontoware.org/ontology#Article
An Associative Memory System with Fuzzy Numbers
en
テクニカルノート
Department of Computer Science & Systems Engineering Muroran Institute of Technology
Department of Applied Mathematics Faculty of Engineering Yokohama National University
Department of Computer Science & Systems Engineering Muroran Institute of Tech
Yukinori Suzuki
Norio Konno
Junji Maeda
We propose an associative memory system (AMS) with fuzzy numbers. The AMS uses a memory matrix and a defuzzification procedure. The memory matrix associates fuzzy response vectors which are transformed into non-fuzzy response vectors by the defuzzification procedure. The performance of the AMS was evaluated by computational experiments. The results of the experiments indicated that the memory capacity of the AMS was larger than that of the standard linear associative memories. In addition the noise tolerance of the MAS was practically the same as that of the linear associative memory using the generalized inverse matrix method.
We propose an associative memory system (AMS) with fuzzy numbers. The AMS uses a memory matrix and a defuzzification procedure. The memory matrix associates fuzzy response vectors which are transformed into non-fuzzy response vectors by the defuzzification procedure. The performance of the AMS was evaluated by computational experiments. The results of the experiments indicated that the memory capacity of the AMS was larger than that of the standard linear associative memories. In addition, the noise tolerance of the MAS was practically the same as that of the linear associative memory using the generalized inverse matrix method.
AN00116647
情報処理学会論文誌
40
1
374-377
1999-01-15
1882-7764