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

FindBook

Google Book

Amazon

博客來

Hierarchical Multi-Task Learning.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Hierarchical Multi-Task Learning./
作者:	Malakouti, Salim.
面頁冊數:	1 online resource (188 pages)
附註:	Source: Dissertations Abstracts International, Volume: 84-10, Section: A.
Contained By:	Dissertations Abstracts International84-10A.
標題:	Patients. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30359502click for full text (PQDT)
ISBN:	9798377676768

Hierarchical Multi-Task Learning.
Malakouti, Salim.

Hierarchical Multi-Task Learning. - 1 online resource (188 pages)

Source: Dissertations Abstracts International, Volume: 84-10, Section: A.

Thesis (Ph.D.)--University of Pittsburgh, 2023.

Includes bibliographical references

Traditionally, machine learning research has adopted methods that were designed to learn one or a set of machine learning tasks independently. However, motivated by our brain's learning mechanism to transfer knowledge from past and other related experiences, recent research has developed and studied methods incorporating target task relationships in the learning algorithms. The area of machine learning in which multiple target tasks are solved simultaneously while exploiting their similarities and underlying structures is known as multi-task learning. Multi-task learning methods (MTL) have proven effective in learning improved machine learning models by facilitating the transfer of knowledge through simultaneously learning a set of target tasks.However, the success of existing multi-task learning methods depends on the extent of the similarity between the target tasks. When tasks are not sufficiently similar, the negative transfer that impacts the quality of the learned models may occur. Therefore, new techniques were adopted that took advantage of task clusters, task-task relatedness, or an asymmetric knowledge transfer. However, none of these techniques are adequate when applied to a large number of heterogeneous tasks organized in a complex hierarchical structure. The abundance of such hierarchies in many domains, including health-care, document classification, and image classification, motivates the development of a new class of multi-task learning methods that can take advantage of these complex hierarchical task relationships.In this thesis, we explore and develop supervised multi-task learning methods that leverage existing task hierarchies to guide the transfer of knowledge between related tasks and evaluate these methods in the context of healthcare applications. First, we propose a simple, yet flexible, approach for learning low-dimensional representations of patients' electronic health records data that are able to overcome challenges related to learning of the models for multiple target tasks from such data. Second, we propose new hierarchical multi-task learning methods that enable the transfer of knowledge in the form of parameter transfer. Third, we study and present new feature-based hierarchical multi-task learning methods that utilize feature transfer instead of parameter transfer solutions to further improve the performance of the models. Finally, we discuss the open questions and problems, and provide ideas for future research directions.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798377676768Subjects--Topical Terms:

1961957
Patients.
Index Terms--Genre/Form:

542853
Electronic books.

Hierarchical Multi-Task Learning.
LDR:03713nmm a2200349K 4500 001 2358942
005 20230830051526.5
006 m o d
007 cr mn ---uuuuu
008 241011s2023 xx obm 000 0 eng d
020 $a 9798377676768
035 $a (MiAaPQ)AAI30359502
035 $a (MiAaPQ)Pittsburgh43700
035 $a AAI30359502
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Malakouti, Salim. $3 3699493
245 1 0 $a Hierarchical Multi-Task Learning.
264 0 $c 2023
300 $a 1 online resource (188 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: Dissertations Abstracts International, Volume: 84-10, Section: A.
500 $a Advisor: Hauskrecht, Milos.
502 $a Thesis (Ph.D.)--University of Pittsburgh, 2023.
504 $a Includes bibliographical references
520 $a Traditionally, machine learning research has adopted methods that were designed to learn one or a set of machine learning tasks independently. However, motivated by our brain's learning mechanism to transfer knowledge from past and other related experiences, recent research has developed and studied methods incorporating target task relationships in the learning algorithms. The area of machine learning in which multiple target tasks are solved simultaneously while exploiting their similarities and underlying structures is known as multi-task learning. Multi-task learning methods (MTL) have proven effective in learning improved machine learning models by facilitating the transfer of knowledge through simultaneously learning a set of target tasks.However, the success of existing multi-task learning methods depends on the extent of the similarity between the target tasks. When tasks are not sufficiently similar, the negative transfer that impacts the quality of the learned models may occur. Therefore, new techniques were adopted that took advantage of task clusters, task-task relatedness, or an asymmetric knowledge transfer. However, none of these techniques are adequate when applied to a large number of heterogeneous tasks organized in a complex hierarchical structure. The abundance of such hierarchies in many domains, including health-care, document classification, and image classification, motivates the development of a new class of multi-task learning methods that can take advantage of these complex hierarchical task relationships.In this thesis, we explore and develop supervised multi-task learning methods that leverage existing task hierarchies to guide the transfer of knowledge between related tasks and evaluate these methods in the context of healthcare applications. First, we propose a simple, yet flexible, approach for learning low-dimensional representations of patients' electronic health records data that are able to overcome challenges related to learning of the models for multiple target tasks from such data. Second, we propose new hierarchical multi-task learning methods that enable the transfer of knowledge in the form of parameter transfer. Third, we study and present new feature-based hierarchical multi-task learning methods that utilize feature transfer instead of parameter transfer solutions to further improve the performance of the models. Finally, we discuss the open questions and problems, and provide ideas for future research directions.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Patients. $3 1961957
650 4 $a Electronic health records. $3 3433800
650 4 $a Disease. $3 705846
650 4 $a Brain research. $3 3561789
650 4 $a Neural networks. $3 677449
650 4 $a Research & development--R&D. $3 3554335
650 4 $a Information science. $3 554358
650 4 $a Neurosciences. $3 588700
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0723
690 $a 0317
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of Pittsburgh. $3 958527
773 0 $t Dissertations Abstracts International $g 84-10A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30359502 $z click for full text (PQDT)