Regularization networks with indefinite kernels

Regularization networks with indefinite kernels
复制标题

具有不定核的正则化网络

DOI:
10.1016/j.jat.2012.10.001
复制
发表时间:
2013-02
影响因子:
0.9
通讯作者:
Qiang Wu
Qiang Wu
中科院分区:
数学3区
文献类型:
--
作者:
Qiang Wu

文献摘要

参考文献

被引文献

相似文献

近年来,不定核学习由于其在各种学习场景中的成功而引起了相当大的关注。在本文中,我们研究的正则化核网络的渐近性质的内核被假定为不确定的,没有通常的限制,对称性和半正定的核方法的传统研究。核的特征在于在相应的核积分的奇异值分解。引入两个再生核Hilbert空间来刻画逼近能力。容量无关的误差界的证明。在再生核Hilbert空间和L ~ 2意义下都得到了快速收敛速度。
Learning with indefinite kernels attracted considerable attention in recent years due to their success in various learning scenarios. In this paper we study the asymptotic properties of the regularization kernel networks where the kernels are assumed to be indefinite, without the usual restrictions of symmetry and positive semi-definiteness as in the traditional study of kernel methods. The kernels are characterized in terms of the singular value decomposition of the corresponding kernel integrals. Two reproducing kernel Hilbert spaces are induced to characterize the approximation ability. Capacity independent error bounds are proved. Fast convergence rates are obtained both in reproducing kernel Hilbert spaces and in L2sense.
DOI: 10.1159/000099415
发表时间: 2007-02
期刊: --
影响因子: --
作者:
J. Hulshof
通讯作者: J. Hulshof
DOI: 10.1016/j.acha.2008.10.002
发表时间: 2009-05
影响因子: 2.5
作者:
Hongwei Sun;Qiang Wu
通讯作者: Hongwei Sun;Qiang Wu
DOI: 10.1090/s0002-9947-1950-0051437-7
发表时间: 1950-01-01
影响因子: 1.3
作者:
ARONSZAJN, N
通讯作者: ARONSZAJN, N
DOI: 10.1162/15324430260185592
发表时间: 2002-03-01
影响因子: 6
作者:
Pekalska, E;Paclík, P;Duin, RPW
通讯作者: Duin, RPW
DOI: --
发表时间: 2005
期刊: --
影响因子: --
作者:
Qiang Wu
通讯作者: Qiang Wu