Tradeoff search methods between interpretability and accuracy of the identification fuzzy systems based on rules /A. E. Yankovskaya, I. V. Gorbunov, I. A. Hodashinsky

Yankovskaya, Anna Efimovna
Электронный ресурс
Другой Автор
Gorbunov, Ivan V.
Hodashinsky, Ilya A.
Источник
Pattern recognition and image analysis 2017 Vol. 27, № 2. P. 243-265
Аннотация
This paper starts a brief historical overview of occurrence and development of fuzzy systems and their applications. Integration methods are proposed to construct a fuzzy system using other AI methods, achieving synergy effect. Accuracy and interpretability are selected as main properties of rule-based fuzzy systems. The tradeoff between interpretability and accuracy is considered to be the actual problem. The purpose of this paper is the in-depth study of the methods and tools to achieve a tradeoff for accuracy and interpretability in rule-based fuzzy systems and to describe our interpretability indexes. A comparison of the existing ways of interpretability estimation has been made We also propose the new way to construct heuristic interpretability indexes as a quantitative measure of interpretability. In the main part of this paper we describe previously used approaches, the current state and original authors’ methods for achieving tradeoff between accuracy and complexity.
Всего оценка: 0
Нет записей для отображения.
 
 
 
02356nab a2200325 c 4500
001
 
 
vtls000617547
003
 
 
RU-ToGU
005
 
 
20171211102300.0
007
 
 
cr |
008
 
 
171208|2017    ru      s         a eng d
024
7
$a 10.1134/S1054661817020134 $2 doi
035
$a to000617547
039
9
$a 201712111023 $b cat202 $c 201712081438 $d VLOAD $y 201712081421 $z VLOAD
040
$a RU-ToGU $b rus $c RU-ToGU
100
1
$a Yankovskaya, Anna Efimovna
245
1
0
$a Tradeoff search methods between interpretability and accuracy of the identification fuzzy systems based on rules $c A. E. Yankovskaya, I. V. Gorbunov, I. A. Hodashinsky
504
$a Библиогр.: 110 назв.
520
3
$a This paper starts a brief historical overview of occurrence and development of fuzzy systems and their applications. Integration methods are proposed to construct a fuzzy system using other AI methods, achieving synergy effect. Accuracy and interpretability are selected as main properties of rule-based fuzzy systems. The tradeoff between interpretability and accuracy is considered to be the actual problem. The purpose of this paper is the in-depth study of the methods and tools to achieve a tradeoff for accuracy and interpretability in rule-based fuzzy systems and to describe our interpretability indexes. A comparison of the existing ways of interpretability estimation has been made We also propose the new way to construct heuristic interpretability indexes as a quantitative measure of interpretability. In the main part of this paper we describe previously used approaches, the current state and original authors’ methods for achieving tradeoff between accuracy and complexity.
653
$a машинное обучение
653
$a распознавание образов
653
$a нечеткое моделирование
655
4
$a статьи в журналах
700
1
$a Gorbunov, Ivan V.
700
1
$a Hodashinsky, Ilya A.
773
0
$t Pattern recognition and image analysis $d 2017 $g Vol. 27, № 2. P. 243-265 $x 1054-6618
852
4
$a RU-ToGU
856
7
$u http://vital.lib.tsu.ru/vital/access/manager/Repository/vtls:000617547
908
$a статья
999
$a VIRTUA               
999
$a VTLSSORT0010*0030*0050*0070*0080*0240*0350*0390*0400*1000*2450*5040*5200*6530*6531*6532*6550*7000*7001*7730*8520*8560*9080*9992
Нет комментариев.
Предмет
статьи в журналах
Резюме
This paper starts a brief historical overview of occurrence and development of fuzzy systems and their applications. Integration methods are proposed to construct a fuzzy system using other AI methods, achieving synergy effect. Accuracy and interpretability are selected as main properties of rule-based fuzzy systems. The tradeoff between interpretability and accuracy is considered to be the actual problem. The purpose of this paper is the in-depth study of the methods and tools to achieve a tradeoff for accuracy and interpretability in rule-based fuzzy systems and to describe our interpretability indexes. A comparison of the existing ways of interpretability estimation has been made We also propose the new way to construct heuristic interpretability indexes as a quantitative measure of interpretability. In the main part of this paper we describe previously used approaches, the current state and original authors’ methods for achieving tradeoff between accuracy and complexity.