LEARNING OF SOFT CLASSIFIER VIA DIFFERENTIAL EVOLUTION

被引:0
作者
Kukal, Jaromir [1 ]
Vysata, Oldrich [1 ]
机构
[1] ICT Prague, DCCE, Prague 16628 6, Dejvice, Czech Republic
来源
MENDEL 2008 | 2008年
关键词
soft classifier; soft sensitivity; constrained gain; optimization; differential evolution;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The study is oriented to two basic aims: define and then realize a classfier with constrained gain and try to learn it to have maximum possible sensitivity. Their meaning is to have maximum possible quality of classification into given number of classes together with suppressed magnification of any input details. It is necessary to define soft classfier, its gain and soft sensitivity, first. The process of soft classfier learning is then described as constrained minimization task on convex domain. But the objective function is non-smooth and non-convex in general, which makes the learning non-trivial and difficult, unfortunately. There is a good chance for sophisticated heuristics of global minimization. One of them, which is based on the competition of various procedures of differential evolution, was used to learn multiclassifier on famous and traditional example of Fishers iris flower classification. The paper is also about the global minimization of non-smooth functions and its role in the domain of artificial intelligence.
引用
收藏
页码:181 / 185
页数:5
相关论文
共 10 条
[1]  
[Anonymous], DIFFERENTIAL EVOLUTI
[2]  
BELTON V, 2002, MULTIPLE CRITERIA DE
[3]  
Fawcett T., 2005, INT J PATTERN RECOGN, V35, P299, DOI [10.1016/j.patrec.2005.10.010, DOI 10.1016/J.PATREC.2005.10.010]
[4]   The use of multiple measurements in taxonomic problems [J].
Fisher, RA .
ANNALS OF EUGENICS, 1936, 7 :179-188
[5]  
Hosmer W., 2000, Applied Logistic Regression, VSecond
[6]   Differential evolution - A simple and efficient heuristic for global optimization over continuous spaces [J].
Storn, R ;
Price, K .
JOURNAL OF GLOBAL OPTIMIZATION, 1997, 11 (04) :341-359
[7]  
Tvrdík J, 2002, FR ART INT, V76, P159
[8]   Adaptive population-based search:: Application to estimation of nonlinear regression parameters [J].
Tvrdik, Josef ;
Krivy, Ivan ;
Misik, Ladislav .
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2007, 52 (02) :713-724
[9]  
Voitsekhovskii M. I., 2001, ENCY MATH
[10]  
Yang X-S, 2008, INTRO MATH OPTIMIZAT