Regularization with dot-product kernels

被引：0

作者：

Smola, AJ ^{[1
]}

Ovári, ZL ^{[1
]}

Williamson, RC ^{[1
]}

机构：

[1] Australian Natl Univ, Dept Engn, Canberra, ACT 2600, Australia

来源：

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 13 | 2001年 / 13卷

关键词：

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：

In this paper we give necessary and sufficient conditions under which kernels of dot product type k(x, y) = k(x - y) satisfy Mercer's condition and thus may be used in Support Vector Machines (SVM), Regularization Networks (RN) or Gaussian Processes (GP). In particular, we show that if the kernel is analytic (i.e. can be expanded in a Taylor series), all expansion coefficients have to be nonnegative. We give an explicit functional form for the feature map by calculating its eigenfunctions and eigenvalues.

引用

页码：308 / 314

页数：7

共 50 条

[21] Families of dot-product snarks on orientable surfaces of low genus
Belcastro, sarah-marie
Kaminski, Jackie
[J]. GRAPHS AND COMBINATORICS, 2007, 23 (03) : 229 - 240
[22] Families of Dot-Product Snarks on Orientable Surfaces of Low Genus
sarah-marie Belcastro
Jackie Kaminski
[J]. Graphs and Combinatorics, 2007, 23 : 229 - 240
[23] GDOT: A Graphene-Based Nanofunction for Dot-Product Computation
Wang, Ning C.
Gonugondla, Sujan K.
Nahlus, Ihab
Shanbhag, Naresh R.
Pop, Eric
[J]. 2016 IEEE SYMPOSIUM ON VLSI TECHNOLOGY, 2016,
[24] Enhancing the Utilization of Dot-Product Engines in Deep Learning Accelerators
Soliman, Taha
Runge, Armin
Ecco, Leonardo
[J]. 2020 IEEE 34TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW 2020), 2020, : 840 - 843
[25] BISDU: A Bit-Serial Dot-Product Unit for Microcontrollers
Metz, David
Kumar, Vineet
Sjalander, Magnus
[J]. ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS, 2023, 22 (05)
[26] In-Situ Computing Through an Analog Dot-Product Engine
Muralimanohar, Naveen
[J]. IEEE MICRO, 2016, 36 (01) : 11 - 12
[27] Hybrid dot-product design for FP-enabled FPGAs
Pasca, Bogdan
[J]. 2019 IEEE 26TH SYMPOSIUM ON COMPUTER ARITHMETIC (ARITH), 2019, : 194 - 196
[28] Multiply accumulate unit optimised for fast dot-product evaluation
Kamp, William
Bainbridge-Smith, Andrew
[J]. ICFPT 2007: INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE TECHNOLOGY, PROCEEDINGS, 2007, : 349 - 352
[29] Optical coherent dot-product chip for sophisticated deep learning regression
Shaofu Xu
Jing Wang
Haowen Shu
Zhike Zhang
Sicheng Yi
Bowen Bai
Xingjun Wang
Jianguo Liu
Weiwen Zou
[J]. Light: Science & Applications, 10
[30] Dot-Product Engine as Computing Memory to Accelerate Machine Learning Algorithms
Hu, Miao
Strachan, John Paul
Li, Zhiyong
Stanley, R. Williams
[J]. PROCEEDINGS OF THE SEVENTEENTH INTERNATIONAL SYMPOSIUM ON QUALITY ELECTRONIC DESIGN ISQED 2016, 2016, : 374 - 379

← 1 2 3 4 5 →