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

Uncovering and Inducing Interpretabl...

Geiger, Atticus Reed.

Linked to FindBook

Google Book

Amazon

博客來

Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models./
Author:	Geiger, Atticus Reed.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
Description:	215 p.
Notes:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
Subject:	Neural networks. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30982545
ISBN:	9798382622958

Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models.
Geiger, Atticus Reed.

Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 215 p.

Source: Dissertations Abstracts International, Volume: 85-11, Section: B.

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

A faithful and interpretable explanation of an AI model's behavior and internal structure is a high-level explanation that is human-intelligible but also consistent with the known, but often opaque low-level causal details of the model. We argue that the theory of causal abstraction provides the mathematical foundations for the desired kinds of model explanations. In the analysis mode, we uncover causal structure using interventions on model-internal states to assess whether an interpretable high-level causal model is a faithful description of a deep learning model. In the training mode, we induce interpretable causal structure using interventions during model training to simulate counterfactuals in the deep learning model's activation space. We show how to uncover and induce causal structures in a variety of case studies on deep learning models that reason over language and/or images.

ISBN: 9798382622958Subjects--Topical Terms:

677449
Neural networks.

Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models.
LDR:01918nmm a2200313 4500 001 2398331
005 20240812064613.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798382622958
035 $a (MiAaPQ)AAI30982545
035 $a (MiAaPQ)STANFORDth321qf7186
035 $a AAI30982545
040 $a MiAaPQ $c MiAaPQ
100 1 $a Geiger, Atticus Reed. $3 3768243
245 1 0 $a Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 215 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
500 $a Advisor: Potts, Christopher;Frank, Michael;Goodman, Noah.
502 $a Thesis (Ph.D.)--Stanford University, 2023.
520 $a A faithful and interpretable explanation of an AI model's behavior and internal structure is a high-level explanation that is human-intelligible but also consistent with the known, but often opaque low-level causal details of the model. We argue that the theory of causal abstraction provides the mathematical foundations for the desired kinds of model explanations. In the analysis mode, we uncover causal structure using interventions on model-internal states to assess whether an interpretable high-level causal model is a faithful description of a deep learning model. In the training mode, we induce interpretable causal structure using interventions during model training to simulate counterfactuals in the deep learning model's activation space. We show how to uncover and induce causal structures in a variety of case studies on deep learning models that reason over language and/or images.
590 $a School code: 0212.
650 4 $a Neural networks. $3 677449
650 4 $a Natural language. $3 3562052
690 $a 0800
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 85-11B.
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=30982545