國立虎尾科技大學 |

Connecting the Dots of Deep Unsupervised Learning : = Theories and Applications.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Connecting the Dots of Deep Unsupervised Learning :/
Reminder of title:	Theories and Applications.
Author:	Zhai, Shuangfei.
Description:	1 online resource (103 pages)
Notes:	Source: Dissertation Abstracts International, Volume: 78-12(E), Section: B.
Subject:	Artificial intelligence. -
Online resource:	click for full text (PQDT)
ISBN:	9780355083804

Connecting the Dots of Deep Unsupervised Learning : = Theories and Applications.
Zhai, Shuangfei.

Connecting the Dots of Deep Unsupervised Learning :Theories and Applications. - 1 online resource (103 pages)

Source: Dissertation Abstracts International, Volume: 78-12(E), Section: B.

Thesis (Ph.D.)--State University of New York at Binghamton, 2017.

Includes bibliographical references

Unsupervised learning is a long standing problem in machine learning. Compared to supervised learning which aims to solve certain well defined prediction problems (classification or regression), unsupervised learning deals with only unlabeled data. This makes unsupervised learning arguably much more challenging than the supervised counterpart, but also much more powerful at the same time. Recently, there has been a huge trend in the machine learning, especially deep learning community in novel unsupervised learning models, which have achieved significant success in various applications. In this thesis work, we aim to bring new insights to this old problem by providing a unified view which connects several popular unsupervised learning models. Furthermore, we also propose to develop novel models show their applications to problems varying from link prediction, semisupervised text classification, anomaly detection and image generation.

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

Mode of access: World Wide Web

ISBN: 9780355083804Subjects--Topical Terms:

559380
Artificial intelligence.
Index Terms--Genre/Form:

554714
Electronic books.

Connecting the Dots of Deep Unsupervised Learning : = Theories and Applications.
LDR:02133ntm a2200325K 4500 001 912160
005 20180608102940.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355083804
035 $a (MiAaPQ)AAI10282226
035 $a (MiAaPQ)binghamton:12489
035 $a AAI10282226
040 $a MiAaPQ $b eng $c MiAaPQ
100 1 $a Zhai, Shuangfei. $3 1184391
245 1 0 $a Connecting the Dots of Deep Unsupervised Learning : $b Theories and Applications.
264 0 $c 2017
300 $a 1 online resource (103 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: 78-12(E), Section: B.
500 $a Adviser: Zhongfei Zhang.
502 $a Thesis (Ph.D.)--State University of New York at Binghamton, 2017.
504 $a Includes bibliographical references
520 $a Unsupervised learning is a long standing problem in machine learning. Compared to supervised learning which aims to solve certain well defined prediction problems (classification or regression), unsupervised learning deals with only unlabeled data. This makes unsupervised learning arguably much more challenging than the supervised counterpart, but also much more powerful at the same time. Recently, there has been a huge trend in the machine learning, especially deep learning community in novel unsupervised learning models, which have achieved significant success in various applications. In this thesis work, we aim to bring new insights to this old problem by providing a unified view which connects several popular unsupervised learning models. Furthermore, we also propose to develop novel models show their applications to problems varying from link prediction, semisupervised text classification, anomaly detection and image generation.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 559380
650 4 $a Computer science. $3 573171
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0984
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a State University of New York at Binghamton. $b Computer Science. $3 845523
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10282226 $z click for full text (PQDT)