Building machines that learn and think about morality

Christopher Burr; Geoff Keeling

Building machines that learn and think about morality

Christopher Burr, Geoff Keeling

Research output: Contribution to conference › Conference Paper › peer-review

90 Downloads (Pure)

Abstract

Lake et al. propose three criteria which, they argue,will bring artiﬁcial intelligence (AI) systems closer to human cognitive abilities. In this paper, we explore the application of these criteria to a particular domain of human cognition: our capacity for moral reasoning. In doing so, we explore a set of considerations relevant to the development of AI moral decision-making. Our main focus is on the relation between dual-process accounts of moral reasoning and model-free/model-based forms of machine learning. We also discuss how work in embodied and situated cognition could provide a valuable perspective on future research.

Original language	English
Number of pages	8
Publication status	Published - 4 Apr 2018
Event	Convention of the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB 2018) - Liverpool, United Kingdom Duration: 4 Apr 2018 → 6 Apr 2018 http://aisb2018.csc.liv.ac.uk

Conference

Conference	Convention of the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB 2018)
Country/Territory	United Kingdom
City	Liverpool
Period	4/04/18 → 6/04/18
Internet address	http://aisb2018.csc.liv.ac.uk

Access to Document

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online at http://aisb2018.csc.liv.ac.uk/proceedings.html . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 624 KB

http://aisb2018.csc.liv.ac.uk/proceedings.html

Cite this

@conference{4d72c717a8f1451d8998a90acd0efe71,

title = "Building machines that learn and think about morality",

abstract = "Lake et al. propose three criteria which, they argue,will bring artiﬁcial intelligence (AI) systems closer to human cognitive abilities. In this paper, we explore the application of these criteria to a particular domain of human cognition: our capacity for moral reasoning. In doing so, we explore a set of considerations relevant to the development of AI moral decision-making. Our main focus is on the relation between dual-process accounts of moral reasoning and model-free/model-based forms of machine learning. We also discuss how work in embodied and situated cognition could provide a valuable perspective on future research.",

author = "Christopher Burr and Geoff Keeling",

year = "2018",

month = apr,

day = "4",

language = "English",

note = "Convention of the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB 2018) ; Conference date: 04-04-2018 Through 06-04-2018",

url = "http://aisb2018.csc.liv.ac.uk",

}

TY - CONF

T1 - Building machines that learn and think about morality

AU - Burr, Christopher

AU - Keeling, Geoff

PY - 2018/4/4

Y1 - 2018/4/4

N2 - Lake et al. propose three criteria which, they argue,will bring artiﬁcial intelligence (AI) systems closer to human cognitive abilities. In this paper, we explore the application of these criteria to a particular domain of human cognition: our capacity for moral reasoning. In doing so, we explore a set of considerations relevant to the development of AI moral decision-making. Our main focus is on the relation between dual-process accounts of moral reasoning and model-free/model-based forms of machine learning. We also discuss how work in embodied and situated cognition could provide a valuable perspective on future research.

AB - Lake et al. propose three criteria which, they argue,will bring artiﬁcial intelligence (AI) systems closer to human cognitive abilities. In this paper, we explore the application of these criteria to a particular domain of human cognition: our capacity for moral reasoning. In doing so, we explore a set of considerations relevant to the development of AI moral decision-making. Our main focus is on the relation between dual-process accounts of moral reasoning and model-free/model-based forms of machine learning. We also discuss how work in embodied and situated cognition could provide a valuable perspective on future research.

M3 - Conference Paper

T2 - Convention of the Society for the Study of Artificial Intelligence and Simulation of Behaviour (AISB 2018)

Y2 - 4 April 2018 through 6 April 2018

ER -

Building machines that learn and think about morality

Abstract

Conference

Access to Document

Fingerprint

Cite this