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

Operationalizing Language for Machin...

Mu, Jesse L.

FindBook

Google Book

Amazon

博客來

Operationalizing Language for Machine Learning: Supervision, Interpretation, and Communication.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Operationalizing Language for Machine Learning: Supervision, Interpretation, and Communication./
作者:	Mu, Jesse L.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
面頁冊數:	149 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
Contained By:	Dissertations Abstracts International85-04B.
標題:	Communication. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30615213
ISBN:	9798380484978

Operationalizing Language for Machine Learning: Supervision, Interpretation, and Communication.
Mu, Jesse L.

Operationalizing Language for Machine Learning: Supervision, Interpretation, and Communication. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 149 p.

Source: Dissertations Abstracts International, Volume: 85-04, Section: B.

Thesis (Ph.D.)--Stanford University, 2023.

Language is a uniquely powerful tool for conceptualizing the world that allows humans to teach, understand, and collaborate with each other. This dissertation surveys three ways in which language can similarly improve the performance and usability of machine learning systems across a variety of tasks and modalities. First, supervision: we use language abstractions to help regularize models and agents for improved performance, even for downstream tasks in vision and reinforcement learning that do not necessarily require language understanding. Second, interpretation: we use language and compositionality to generate explanations of the neurons inside deep neural networks, allowing us to understand and even control model behavior. Finally, communication: we study a class of multiagent signaling games, helping agents learn more robust and interpretable languages by encouraging them to express the generalizations encoded in human languages.

ISBN: 9798380484978Subjects--Topical Terms:

524709
Communication.

Operationalizing Language for Machine Learning: Supervision, Interpretation, and Communication.
LDR:02007nmm a2200337 4500 001 2404475
005 20241213095544.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798380484978
035 $a (MiAaPQ)AAI30615213
035 $a (MiAaPQ)STANFORDtb801sk9437
035 $a AAI30615213
040 $a MiAaPQ $c MiAaPQ
100 1 $a Mu, Jesse L. $3 3774790
245 1 0 $a Operationalizing Language for Machine Learning: Supervision, Interpretation, and Communication.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 149 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
500 $a Advisor: Andreas, Jacob;Liang, Percy.
502 $a Thesis (Ph.D.)--Stanford University, 2023.
520 $a Language is a uniquely powerful tool for conceptualizing the world that allows humans to teach, understand, and collaborate with each other. This dissertation surveys three ways in which language can similarly improve the performance and usability of machine learning systems across a variety of tasks and modalities. First, supervision: we use language abstractions to help regularize models and agents for improved performance, even for downstream tasks in vision and reinforcement learning that do not necessarily require language understanding. Second, interpretation: we use language and compositionality to generate explanations of the neurons inside deep neural networks, allowing us to understand and even control model behavior. Finally, communication: we study a class of multiagent signaling games, helping agents learn more robust and interpretable languages by encouraging them to express the generalizations encoded in human languages.
590 $a School code: 0212.
650 4 $a Communication. $3 524709
650 4 $a Linguistics. $3 524476
650 4 $a Codes. $3 3560019
650 4 $a Games. $3 525308
690 $a 0290
690 $a 0459
690 $a 0800
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 85-04B.
790 $a 0212
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30615213