國立虎尾科技大學 |

Building More Expressive Structured Models.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Building More Expressive Structured Models./
作者:	Li, Yujia.
面頁冊數:	1 online resource (114 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-04(E), Section: B.
Contained By:	Dissertation Abstracts International79-04B(E).
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9780355448245

Building More Expressive Structured Models.
Li, Yujia.

Building More Expressive Structured Models. - 1 online resource (114 pages)

Source: Dissertation Abstracts International, Volume: 79-04(E), Section: B.

Thesis (Ph.D.)--University of Toronto (Canada), 2017.

Includes bibliographical references

Structured data and structured problems are common in machine learning, and they appear in many applications from computer vision, natural language understanding, information retrieval, computational biology, and many more. Compared to unstructured problems, where the input data is represented as a vector of independent feature values and output is a scalar prediction like a class label or regression value, both the input and output for structured problems may be objects with internal structure, like sequences, grids, trees or general graphs.

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

Mode of access: World Wide Web

ISBN: 9780355448245Subjects--Topical Terms:

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

554714
Electronic books.

Building More Expressive Structured Models.
LDR:03423ntm a2200385Ki 4500 001 916760
005 20180928111500.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355448245
035 $a (MiAaPQ)AAI10257596
035 $a (MiAaPQ)toronto:15428
035 $a AAI10257596
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Li, Yujia. $3 1190584
245 1 0 $a Building More Expressive Structured Models.
264 0 $c 2017
300 $a 1 online resource (114 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: 79-04(E), Section: B.
500 $a Adviser: Richard S. Zemel.
502 $a Thesis (Ph.D.)--University of Toronto (Canada), 2017.
504 $a Includes bibliographical references
520 $a Structured data and structured problems are common in machine learning, and they appear in many applications from computer vision, natural language understanding, information retrieval, computational biology, and many more. Compared to unstructured problems, where the input data is represented as a vector of independent feature values and output is a scalar prediction like a class label or regression value, both the input and output for structured problems may be objects with internal structure, like sequences, grids, trees or general graphs.
520 $a Effectively exploiting the structure in the problems can help build efficient prediction models that significantly improve performance. The complexity of the structures requires expressive models that have enough representation capabilities. However, increased model complexity usually leads to increased inference complexity. A key challenge in building more expressive structured models is therefore to balance the model complexity and inference complexity, and explore models that are both expressive enough and have efficient inference.
520 $a In this thesis, I present our work in the direction of building more expressive structured models, from developing more expressive structured output models, to semi-supervised learning of structured models, and then structured neural network models.
520 $a The first technical part of the thesis describes a model that uses a new family of expressive high order pattern potentials, for which we characterized the theoretical properties and developed efficient inference and learning algorithms. Next we study semi-supervised learning algorithms for structured prediction problems that can help improve prediction performance by using unlabeled data. Motivated by our observation that standard structured models with iterative inference algorithms can be converted to neural networks, we study in particular structured neural network models for structured problems, and propose a new model that can handle prediction problems on graphs.
520 $a Discussions about promising future directions are presented at the end of each technical chapter as well as at the end of the thesis.
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 University of Toronto (Canada). $b Computer Science. $3 845521
773 0 $t Dissertation Abstracts International $g 79-04B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10257596 $z click for full text (PQDT)