東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Linked to FindBook

Google Book

Amazon

博客來

Explaining Transformers Using Class Activation Map.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Explaining Transformers Using Class Activation Map./
Author:	Pan, Deng.
Description:	1 online resource (40 pages)
Notes:	Source: Masters Abstracts International, Volume: 83-12.
Contained By:	Masters Abstracts International83-12.
Subject:	Computer science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28971203click for full text (PQDT)
ISBN:	9798819362457

Explaining Transformers Using Class Activation Map.
Pan, Deng.

Explaining Transformers Using Class Activation Map. - 1 online resource (40 pages)

Source: Masters Abstracts International, Volume: 83-12.

Thesis (M.S.)--Wayne State University, 2022.

Includes bibliographical references

Transformer based pretrained NLP models have became the primary choices in almost all NLP tasks because of their overall outstanding performance and robustness. However, it is still an open problem to understand a transformer based model's prediction due to the complexity of the stacked multi-head self-attention architectures. In this thesis, we utilize the idea behind class activation map (CAM) technique in explaining image classification tasks, and propose class activation transformer (CAT) for explaining the general transformer framework. We also analyze the technical soundness of our CAT and other gradient based Deep Neural Network explanation. Experiments demonstrate that CAT+transformer can be utilized as a general interpretation+prediction framework in both NLP and CV tasks.

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

Mode of access: World Wide Web

ISBN: 9798819362457Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Interpretable machine learningIndex Terms--Genre/Form:

542853
Electronic books.

Explaining Transformers Using Class Activation Map.
LDR:02061nmm a2200373K 4500 001 2363273
005 20231121104552.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798819362457
035 $a (MiAaPQ)AAI28971203
035 $a AAI28971203
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Pan, Deng. $0 (orcid)0000-0003-3037-8912 $3 3689978
245 1 0 $a Explaining Transformers Using Class Activation Map.
264 0 $c 2022
300 $a 1 online resource (40 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: Masters Abstracts International, Volume: 83-12.
500 $a Advisor: Zhu, Dongxiao.
502 $a Thesis (M.S.)--Wayne State University, 2022.
504 $a Includes bibliographical references
520 $a Transformer based pretrained NLP models have became the primary choices in almost all NLP tasks because of their overall outstanding performance and robustness. However, it is still an open problem to understand a transformer based model's prediction due to the complexity of the stacked multi-head self-attention architectures. In this thesis, we utilize the idea behind class activation map (CAM) technique in explaining image classification tasks, and propose class activation transformer (CAT) for explaining the general transformer framework. We also analyze the technical soundness of our CAT and other gradient based Deep Neural Network explanation. Experiments demonstrate that CAT+transformer can be utilized as a general interpretation+prediction framework in both NLP and CV tasks.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 523869
650 4 $a Computer engineering. $3 621879
650 4 $a Artificial intelligence. $3 516317
653 $a Interpretable machine learning
653 $a Transformers
653 $a Class activation map
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0984
690 $a 0464
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Wayne State University. $b Computer Science. $3 1030863
773 0 $t Masters Abstracts International $g 83-12.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28971203 $z click for full text (PQDT)