國立虎尾科技大學 |

Kernels and Geometry of Machine Learning.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Kernels and Geometry of Machine Learning./
作者:	Moeller, John.
面頁冊數:	1 online resource (91 pages)
附註:	Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9781369775273

Kernels and Geometry of Machine Learning.
Moeller, John.

Kernels and Geometry of Machine Learning. - 1 online resource (91 pages)

Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.

Thesis (Ph.D.)--The University of Utah, 2017.

Includes bibliographical references

The contributions in the area of kernelized learning techniques have expanded beyond a few basic kernel functions to general kernel functions that could be learned along with the rest of a statistical learning model. This dissertation aims to explore various directions in kernel learning, a setting where we can learn not only a model, but also glean information about the geometry of the data from which we learn, by learning a positive definite (p.d.) kernel. Throughout, we can exploit several properties of kernels that relate to their geometry --- a facet that is often overlooked.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369775273Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Kernels and Geometry of Machine Learning.
LDR:02738ntm a2200349K 4500 001 915292
005 20180727125212.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9781369775273
035 $a (MiAaPQ)AAI10266475
035 $a (MiAaPQ)utah:13777
035 $a AAI10266475
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Moeller, John. $3 1188606
245 1 0 $a Kernels and Geometry of Machine Learning.
264 0 $c 2017
300 $a 1 online resource (91 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
500 $a Adviser: Suresh Venkatasubramanian.
502 $a Thesis (Ph.D.)--The University of Utah, 2017.
504 $a Includes bibliographical references
520 $a The contributions in the area of kernelized learning techniques have expanded beyond a few basic kernel functions to general kernel functions that could be learned along with the rest of a statistical learning model. This dissertation aims to explore various directions in kernel learning, a setting where we can learn not only a model, but also glean information about the geometry of the data from which we learn, by learning a positive definite (p.d.) kernel. Throughout, we can exploit several properties of kernels that relate to their geometry --- a facet that is often overlooked.
520 $a We revisit some of the necessary mathematical background required to understand kernel learning in context, such as reproducing kernel Hilbert spaces (RKHSs), the reproducing property, the representer theorem, etc. We then cover kernelized learning with support vector machines (SVMs), multiple kernel learning (MKL), and localized kernel learning (LKL). We move on to Bochner's theorem, a tool vital to one of the kernel learning areas we explore.
520 $a The main portion of the thesis is divided into two parts: (1) kernel learning with SVMs, a.k.a. MKL, and (2) learning based on Bochner's theorem. In the first part, we present efficient, accurate, and scalable algorithms based on the SVM, one that exploits multiplicative weight updates (MWU), and another that exploits local geometry. In the second part, we use Bochner's theorem to incorporate a kernel into a neural network and discover that kernel learning in this fashion, continuous kernel learning (CKL), is superior even to MKL.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Artificial intelligence. $3 559380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The University of Utah. $b Computing. $3 1188607
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10266475 $z click for full text (PQDT)