The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Prestasi algoritma pembelajaran berasaskan kernel, seperti SVM, sangat bergantung pada pilihan parameter kernel yang betul. Adalah wajar untuk mesin kernel berfungsi pada parameter kernel optimum yang menyesuaikan dengan baik kepada data input dan tugas pembelajaran. Dalam makalah ini, kami membentangkan kaedah baru untuk memilih parameter kernel Gaussian dengan memaksimumkan kriteria pemisahan kelas, yang mengukur taburan data dalam ruang ciri yang disebabkan kernel, dan tidak berubah di bawah sebarang transformasi linear bukan tunggal. Keputusan eksperimen menunjukkan bahawa kedua-dua kebolehpisahan kelas data dalam ruang ciri teraruh kernel dan prestasi pengelasan pengelas SVM dipertingkatkan dengan menggunakan parameter kernel optimum.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Xu YANG, HuiLin XIONG, Xin YANG, "Optimal Gaussian Kernel Parameter Selection for SVM Classifier" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 12, pp. 3352-3358, December 2010, doi: 10.1587/transinf.E93.D.3352.
Abstract: The performance of the kernel-based learning algorithms, such as SVM, depends heavily on the proper choice of the kernel parameter. It is desirable for the kernel machines to work on the optimal kernel parameter that adapts well to the input data and the learning tasks. In this paper, we present a novel method for selecting Gaussian kernel parameter by maximizing a class separability criterion, which measures the data distribution in the kernel-induced feature space, and is invariant under any non-singular linear transformation. The experimental results show that both the class separability of the data in the kernel-induced feature space and the classification performance of the SVM classifier are improved by using the optimal kernel parameter.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.3352/_p
Salinan
@ARTICLE{e93-d_12_3352,
author={Xu YANG, HuiLin XIONG, Xin YANG, },
journal={IEICE TRANSACTIONS on Information},
title={Optimal Gaussian Kernel Parameter Selection for SVM Classifier},
year={2010},
volume={E93-D},
number={12},
pages={3352-3358},
abstract={The performance of the kernel-based learning algorithms, such as SVM, depends heavily on the proper choice of the kernel parameter. It is desirable for the kernel machines to work on the optimal kernel parameter that adapts well to the input data and the learning tasks. In this paper, we present a novel method for selecting Gaussian kernel parameter by maximizing a class separability criterion, which measures the data distribution in the kernel-induced feature space, and is invariant under any non-singular linear transformation. The experimental results show that both the class separability of the data in the kernel-induced feature space and the classification performance of the SVM classifier are improved by using the optimal kernel parameter.},
keywords={},
doi={10.1587/transinf.E93.D.3352},
ISSN={1745-1361},
month={December},}
Salinan
TY - JOUR
TI - Optimal Gaussian Kernel Parameter Selection for SVM Classifier
T2 - IEICE TRANSACTIONS on Information
SP - 3352
EP - 3358
AU - Xu YANG
AU - HuiLin XIONG
AU - Xin YANG
PY - 2010
DO - 10.1587/transinf.E93.D.3352
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2010
AB - The performance of the kernel-based learning algorithms, such as SVM, depends heavily on the proper choice of the kernel parameter. It is desirable for the kernel machines to work on the optimal kernel parameter that adapts well to the input data and the learning tasks. In this paper, we present a novel method for selecting Gaussian kernel parameter by maximizing a class separability criterion, which measures the data distribution in the kernel-induced feature space, and is invariant under any non-singular linear transformation. The experimental results show that both the class separability of the data in the kernel-induced feature space and the classification performance of the SVM classifier are improved by using the optimal kernel parameter.
ER -