國立虎尾科技大學 |

Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models./
Author:	Geiger, Atticus Reed.
Description:	1 online resource (215 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
Contained By:	Dissertations Abstracts International85-11B.
Subject:	Neural networks. -
Online resource:	click for full text (PQDT)
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. - 1 online resource (215 pages)

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

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

Includes bibliographical references

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.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798382622958Subjects--Topical Terms:

1011215
Neural networks.
Index Terms--Genre/Form:

554714
Electronic books.

Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models.
LDR:02142ntm a22003257 4500 001 1146427
005 20240812064613.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798382622958
035 $a (MiAaPQ)AAI30982545
035 $a (MiAaPQ)STANFORDth321qf7186
035 $a AAI30982545
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Geiger, Atticus Reed. $3 1471815
245 1 0 $a Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models.
264 0 $c 2023
300 $a 1 online resource (215 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: 85-11, Section: B.
500 $a Advisor: Potts, Christopher;Frank, Michael;Goodman, Noah.
502 $a Thesis (Ph.D.)--Stanford University, 2023.
504 $a Includes bibliographical references
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.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Neural networks. $3 1011215
650 4 $a Natural language. $3 1468611
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Stanford University. $3 1184533
773 0 $t Dissertations Abstracts International $g 85-11B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30982545 $z click for full text (PQDT)