Hilbert–Schmidt component analysis
We propose a feature extraction algorithm, based on the Hilbert–Schmidt independence criterion (HSIC) and the maximum dependence – minimum redundancy approach. Experiments with classification data sets demonstrate that suggested Hilbert–Schmidt component analysis (HSCA) algorithm in certain cases ma...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Vilnius University Press
2016-12-01
|
| Series: | Lietuvos Matematikos Rinkinys |
| Subjects: | |
| Online Access: | https://www.journals.vu.lt/LMR/article/view/14932 |
| _version_ | 1818764919097524224 |
|---|---|
| author | Povilas Daniušis Pranas Vaitkus Linas Petkevičius |
| author_facet | Povilas Daniušis Pranas Vaitkus Linas Petkevičius |
| author_sort | Povilas Daniušis |
| collection | DOAJ |
| description | We propose a feature extraction algorithm, based on the Hilbert–Schmidt independence criterion (HSIC) and the maximum dependence – minimum redundancy approach. Experiments with classification data sets demonstrate that suggested Hilbert–Schmidt component analysis (HSCA) algorithm in certain cases may be more efficient than other considered approaches. |
| first_indexed | 2024-12-18T08:09:50Z |
| format | Article |
| id | doaj.art-169de564ee4d495f9354548f9edac860 |
| institution | Directory Open Access Journal |
| issn | 0132-2818 2335-898X |
| language | English |
| last_indexed | 2024-12-18T08:09:50Z |
| publishDate | 2016-12-01 |
| publisher | Vilnius University Press |
| record_format | Article |
| series | Lietuvos Matematikos Rinkinys |
| spelling | doaj.art-169de564ee4d495f9354548f9edac8602022-12-21T21:14:55ZengVilnius University PressLietuvos Matematikos Rinkinys0132-28182335-898X2016-12-0157A10.15388/LMR.A.2016.02Hilbert–Schmidt component analysisPovilas Daniušis0Pranas Vaitkus1Linas Petkevičius2Vilnius UniversityVilnius UniversityVilnius UniversityWe propose a feature extraction algorithm, based on the Hilbert–Schmidt independence criterion (HSIC) and the maximum dependence – minimum redundancy approach. Experiments with classification data sets demonstrate that suggested Hilbert–Schmidt component analysis (HSCA) algorithm in certain cases may be more efficient than other considered approaches.https://www.journals.vu.lt/LMR/article/view/14932feature extractiondimensionality reductionHSCAHilbert–Schmidt independence criterionkernel methods |
| spellingShingle | Povilas Daniušis Pranas Vaitkus Linas Petkevičius Hilbert–Schmidt component analysis Lietuvos Matematikos Rinkinys feature extraction dimensionality reduction HSCA Hilbert–Schmidt independence criterion kernel methods |
| title | Hilbert–Schmidt component analysis |
| title_full | Hilbert–Schmidt component analysis |
| title_fullStr | Hilbert–Schmidt component analysis |
| title_full_unstemmed | Hilbert–Schmidt component analysis |
| title_short | Hilbert–Schmidt component analysis |
| title_sort | hilbert schmidt component analysis |
| topic | feature extraction dimensionality reduction HSCA Hilbert–Schmidt independence criterion kernel methods |
| url | https://www.journals.vu.lt/LMR/article/view/14932 |
| work_keys_str_mv | AT povilasdaniusis hilbertschmidtcomponentanalysis AT pranasvaitkus hilbertschmidtcomponentanalysis AT linaspetkevicius hilbertschmidtcomponentanalysis |