Tractable Probabilistic Models for Ethical AI

Vaishak Belle

doi:10.1007/978-3-031-16663-1_1

Tractable Probabilistic Models for Ethical AI

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

Among the many ethical dimensions that arise in the use of ML technology, three stand out as immediate and profound: enabling the interpretability of the underlying decision boundary, addressing the potential for learned algorithms to become biased against certain groups, and capturing blame and responsibility for a system's outcomes. In this talk, we advocate for a research program that seeks to bridge tractable (probabilistic) models for knowledge acquisition with rich models of autonomous agency that draw on philosophical notions of beliefs, intentions, causes and effects.

Original language	English
Title of host publication	Graph-Based Representation and Reasoning
Editors	Tanya Braun, Diana Cristea, Robert Jäschke
Publisher	Springer
Pages	3-8
Number of pages	6
ISBN (Electronic)	978-3-031-16663-1
ISBN (Print)	978-3-031-16662-4
DOIs	https://doi.org/10.1007/978-3-031-16663-1_1
Publication status	Published - 11 Sept 2022
Event	27th International Conference on Conceptual Structures - Münster, Germany Duration: 12 Sept 2022 → 15 Sept 2022 https://iccs-conference.org/

Publication series

Name	Lecture Notes in Computer Science
Volume	13403
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	27th International Conference on Conceptual Structures
Abbreviated title	ICCS 2022
Country/Territory	Germany
City	Münster
Period	12/09/22 → 15/09/22
Internet address	https://iccs-conference.org/

Access to Document

10.1007/978-3-031-16663-1_1Licence: All Rights Reserved

Tractable Probabilistic_BELLE_DOA02092022_AFVAccepted author manuscript, 76.3 KBLicence: Creative Commons: Attribution (CC-BY)

https://link.springer.com/chapter/10.1007/978-3-031-16663-1_1Licence: All Rights Reserved

Cite this

@inproceedings{f599bfdc8076408c9604801564579db8,

title = "Tractable Probabilistic Models for Ethical AI",

abstract = "Among the many ethical dimensions that arise in the use of ML technology, three stand out as immediate and profound: enabling the interpretability of the underlying decision boundary, addressing the potential for learned algorithms to become biased against certain groups, and capturing blame and responsibility for a system's outcomes. In this talk, we advocate for a research program that seeks to bridge tractable (probabilistic) models for knowledge acquisition with rich models of autonomous agency that draw on philosophical notions of beliefs, intentions, causes and effects.",

author = "Vaishak Belle",

note = "Funding Information: This article is a written version of the keynote to be given at 27th International Conference on Conceptual Structures, September 2022, M{\"u}nster, Germany. A preliminary version of this work was also presented at the Critical Perspectives on Artificial Intelligence Ethics Conference in Edinburgh, UK, 2020. The author was supported by a Royal Society University Research Fellowship. Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 27th International Conference on Conceptual Structures, ICCS 2022 ; Conference date: 12-09-2022 Through 15-09-2022",

year = "2022",

month = sep,

day = "11",

doi = "10.1007/978-3-031-16663-1_1",

language = "English",

isbn = "978-3-031-16662-4",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "3--8",

editor = "Tanya Braun and Diana Cristea and Robert J{\"a}schke",

booktitle = "Graph-Based Representation and Reasoning",

address = "United Kingdom",

url = "https://iccs-conference.org/",

}

TY - GEN

T1 - Tractable Probabilistic Models for Ethical AI

AU - Belle, Vaishak

N1 - Funding Information: This article is a written version of the keynote to be given at 27th International Conference on Conceptual Structures, September 2022, Münster, Germany. A preliminary version of this work was also presented at the Critical Perspectives on Artificial Intelligence Ethics Conference in Edinburgh, UK, 2020. The author was supported by a Royal Society University Research Fellowship. Publisher Copyright: © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

PY - 2022/9/11

Y1 - 2022/9/11

N2 - Among the many ethical dimensions that arise in the use of ML technology, three stand out as immediate and profound: enabling the interpretability of the underlying decision boundary, addressing the potential for learned algorithms to become biased against certain groups, and capturing blame and responsibility for a system's outcomes. In this talk, we advocate for a research program that seeks to bridge tractable (probabilistic) models for knowledge acquisition with rich models of autonomous agency that draw on philosophical notions of beliefs, intentions, causes and effects.

AB - Among the many ethical dimensions that arise in the use of ML technology, three stand out as immediate and profound: enabling the interpretability of the underlying decision boundary, addressing the potential for learned algorithms to become biased against certain groups, and capturing blame and responsibility for a system's outcomes. In this talk, we advocate for a research program that seeks to bridge tractable (probabilistic) models for knowledge acquisition with rich models of autonomous agency that draw on philosophical notions of beliefs, intentions, causes and effects.

U2 - 10.1007/978-3-031-16663-1_1

DO - 10.1007/978-3-031-16663-1_1

M3 - Conference contribution

SN - 978-3-031-16662-4

T3 - Lecture Notes in Computer Science

SP - 3

EP - 8

BT - Graph-Based Representation and Reasoning

A2 - Braun, Tanya

A2 - Cristea, Diana

A2 - Jäschke, Robert

PB - Springer

T2 - 27th International Conference on Conceptual Structures

Y2 - 12 September 2022 through 15 September 2022

ER -