東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

The Big Picture: Loss Functions at t...

Kannan, Karthik.

FindBook

Google Book

Amazon

博客來

The Big Picture: Loss Functions at the Dataset Level.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	The Big Picture: Loss Functions at the Dataset Level./
作者:	Kannan, Karthik.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2017,
面頁冊數:	35 p.
附註:	Source: Masters Abstracts International, Volume: 56-05.
Contained By:	Masters Abstracts International56-05(E).
標題:	Computer science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10274752
ISBN:	9781369865561

The Big Picture: Loss Functions at the Dataset Level.
Kannan, Karthik.

The Big Picture: Loss Functions at the Dataset Level. - Ann Arbor : ProQuest Dissertations & Theses, 2017 - 35 p.

Source: Masters Abstracts International, Volume: 56-05.

Thesis (M.S.)--University of Colorado at Boulder, 2017.

Loss functions play a key role in machine learning optimization problems. Even with their widespread use throughout the field, selecting a loss function tailored to a specific problem is more art than science. Literature on the properties of loss functions that might help a practitioner make an informed choice about these loss functions is sparse.

ISBN: 9781369865561Subjects--Topical Terms:

523869
Computer science.

The Big Picture: Loss Functions at the Dataset Level.
LDR:01682nmm a2200289 4500 001 2126477
005 20171121080732.5
008 180830s2017 ||||||||||||||||| ||eng d
020 $a 9781369865561
035 $a (MiAaPQ)AAI10274752
035 $a AAI10274752
040 $a MiAaPQ $c MiAaPQ
100 1 $a Kannan, Karthik. $3 3288580
245 1 4 $a The Big Picture: Loss Functions at the Dataset Level.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2017
300 $a 35 p.
500 $a Source: Masters Abstracts International, Volume: 56-05.
500 $a Adviser: Rafael M. Frongillo.
502 $a Thesis (M.S.)--University of Colorado at Boulder, 2017.
520 $a Loss functions play a key role in machine learning optimization problems. Even with their widespread use throughout the field, selecting a loss function tailored to a specific problem is more art than science. Literature on the properties of loss functions that might help a practitioner make an informed choice about these loss functions is sparse.
520 $a In this thesis, we motivate research on the behavior of loss functions at the level of the dataset as a whole. We begin with a simple experiment that illustrates the differences in these loss functions. We then move on to a well-known attribute of perhaps the most ubiquitous loss function, the squared error. We will then characterize all loss functions that exhibit this property. Finally we end with extensions and possible directions of research in this field.
590 $a School code: 0051.
650 4 $a Computer science. $3 523869
690 $a 0984
710 2 $a University of Colorado at Boulder. $b Computer Science. $3 1018560
773 0 $t Masters Abstracts International $g 56-05(E).
790 $a 0051
791 $a M.S.
792 $a 2017
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10274752