A Kernel Function Optimization and Selection Algorithm Based on Cost Function Maximization

被引：0
|
作者：
Zhu, Bin [1 ]
Cheng, Zhengdong [1 ]
Wang, Hui [2 ]
机构：
[1] Inst Elect Engn, Dept Optoelect, Hefei, Peoples R China
[2] Chinese Acad Sci, Inst Intelligent Machines, Hefei, Peoples R China
来源：
2013 IEEE INTERNATIONAL CONFERENCE ON IMAGING SYSTEMS AND TECHNIQUES (IST 2013) | 2013年
关键词：
kernel methods; cost function; kernel function; optimization and selection; Kernel RLS;
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：
Kernel function optimization and selection is an open and challenging problem in statistic learning theory and kernel methods research area at present. The existing kernel optimization algorithms usually work in specific application, and it is efficient when used with one kind of kernel function. A kernel optimization and selection algorithm based on cost function maximization is proposed. Compared with present methods, it was applied to different kinds of kernel functions and it integrates kernel optimization and selection. The proposed method is applied to the application of infrared (IR) dim and small target detection based on Kernel RLS (KRLS) algorithm. The validity of the optimization and selection method is demonstrated by experiments.
引用
收藏
页码：259 / 263
页数：5
相关论文
共 50 条
  • [41] Research and Application of High Dimensional Discrete Data Clustering Algorithm Based on Kernel Function
    Ye, Fulan
    2018 5TH INTERNATIONAL CONFERENCE ON ELECTRICAL & ELECTRONICS ENGINEERING AND COMPUTER SCIENCE (ICEEECS 2018), 2018, : 15 - 18
  • [42] Cost Function Selection for a Graph-Based Segmentation in OCT Retinal Images
    Gonzalez, A.
    Penedo, M. G.
    Vazquez, S. G.
    Novo, J.
    Charlon, P.
    COMPUTER AIDED SYSTEMS THEORY, PT II, 2013, 8112 : 125 - 132
  • [43] A large-update interior-point algorithm for convex quadratic semi-definite optimization based on a new kernel function
    Ming Wang Zhang
    Acta Mathematica Sinica, English Series, 2012, 28 : 2313 - 2328
  • [44] An interior-point algorithm for linearly constrained convex optimization based on kernel function and application in non-negative matrix factorization
    Fathi-Hafshejani, S.
    Moaberfard, Z.
    OPTIMIZATION AND ENGINEERING, 2020, 21 (03) : 1019 - 1051
  • [45] A Pattern Learning Method Based on Kernel Function
    Tai, Liting
    Qin, Sujuan
    Guo, Fenzhuo
    PROCEEDINGS OF 2017 2ND INTERNATIONAL CONFERENCE ON COMMUNICATION AND INFORMATION SYSTEMS (ICCIS 2017), 2015, : 324 - 328
  • [46] A Clustering Algorithm via Kernel Function and Locality Preserving Projections
    Zhan, Mengmeng
    Lu, Guangquan
    Wen, Guoqiu
    Zhang, Leyuan
    Wu, Lin
    2019 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2019), 2019, : 2620 - 2625
  • [47] On cost function properties in analog circuit optimization
    Nussdorfer, A
    Bürmen, A
    Puhan, J
    Tuma, T
    INFORMACIJE MIDEM-JOURNAL OF MICROELECTRONICS ELECTRONIC COMPONENTS AND MATERIALS, 2004, 34 (02): : 95 - 101
  • [48] An interior-point algorithm for linearly constrained convex optimization based on kernel function and application in non-negative matrix factorization
    S. Fathi-Hafshejani
    Z. Moaberfard
    Optimization and Engineering, 2020, 21 : 1019 - 1051
  • [49] An efficient twice parameterized trigonometric kernel function for linear optimization
    Mousaab Bouafia
    Adnan Yassine
    Optimization and Engineering, 2020, 21 : 651 - 672
  • [50] An efficient twice parameterized trigonometric kernel function for linear optimization
    Bouafia, Mousaab
    Yassine, Adnan
    OPTIMIZATION AND ENGINEERING, 2020, 21 (02) : 651 - 672
12345