No Cover Image

Conference Paper/Proceeding/Abstract 39 views

Regret from cognition to code

Alan Dix Orcid Logo, Genovefa Kefalidou Orcid Logo

CIFMA 2021, Software Engineering and Formal Methods. SEFM 2021 Collocated Workshops, Volume: 13230

Swansea University Author: Alan Dix Orcid Logo

Abstract

Regret seems like a very negative emotion, sometimes even debilitating. However, emotions usually have a purpose -- in the case of regret to help us learn from past mistakes. In this paper we first present an informal cognitive account of the way regret is built from a wide range of both primitive a...

Full description

Published in: CIFMA 2021, Software Engineering and Formal Methods. SEFM 2021 Collocated Workshops
Published: Springer
URI: https://cronfa.swan.ac.uk/Record/cronfa59810
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2022-04-12T18:52:35Z
last_indexed 2022-06-07T03:31:58Z
id cronfa59810
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>59810</id><entry>2022-04-12</entry><title>Regret from cognition to code</title><swanseaauthors><author><sid>e31e47c578b2a6a39949aa7f149f4cf9</sid><ORCID>0000-0002-5242-7693</ORCID><firstname>Alan</firstname><surname>Dix</surname><name>Alan Dix</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2022-04-12</date><deptcode>SCS</deptcode><abstract>Regret seems like a very negative emotion, sometimes even debilitating. However, emotions usually have a purpose -- in the case of regret to help us learn from past mistakes. In this paper we first present an informal cognitive account of the way regret is built from a wide range of both primitive and more sophisticated mental abilities. The story includes Skinner-level learning, imagination, emotion, and counter-factual reasoning. When it works well this system focuses attention on aspects of past events where a small difference in behaviour would have made a big difference in outcome -- precisely the most important lessons to learn. The paper then takes elements of this cognitive account and creates a computational model, which can be applied in simple learning situations. We find that even this simplified model boosts machine learning reducing the number of required training samples by a factor of 3--10. This has theoretical implications in terms of understanding emotion and mechanisms that may cast light on related phenomena such as creativity and serendipity. It also has potential practical applications in improving machine leaning and maybe even alleviating dysfunctional regret.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>CIFMA 2021, Software Engineering and Formal Methods. SEFM 2021 Collocated Workshops</journal><volume>13230</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>Springer</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Regret Cognitive modelEmotionMachine learningHuman-Computer Interaction</keywords><publishedDay>0</publishedDay><publishedMonth>0</publishedMonth><publishedYear>0</publishedYear><publishedDate>0001-01-01</publishedDate><doi/><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm>Not Required</apcterm><funders/><projectreference/><lastEdited>2022-07-28T07:26:32.3063977</lastEdited><Created>2022-04-12T19:36:10.5027749</Created><path><level id="1">College of Science</level><level id="2">Computer Science</level></path><authors><author><firstname>Alan</firstname><surname>Dix</surname><orcid>0000-0002-5242-7693</orcid><order>1</order></author><author><firstname>Genovefa</firstname><surname>Kefalidou</surname><orcid>0000-0002-2889-7564</orcid><order>2</order></author></authors><documents/><OutputDurs/></rfc1807>
spelling v2 59810 2022-04-12 Regret from cognition to code e31e47c578b2a6a39949aa7f149f4cf9 0000-0002-5242-7693 Alan Dix Alan Dix true false 2022-04-12 SCS Regret seems like a very negative emotion, sometimes even debilitating. However, emotions usually have a purpose -- in the case of regret to help us learn from past mistakes. In this paper we first present an informal cognitive account of the way regret is built from a wide range of both primitive and more sophisticated mental abilities. The story includes Skinner-level learning, imagination, emotion, and counter-factual reasoning. When it works well this system focuses attention on aspects of past events where a small difference in behaviour would have made a big difference in outcome -- precisely the most important lessons to learn. The paper then takes elements of this cognitive account and creates a computational model, which can be applied in simple learning situations. We find that even this simplified model boosts machine learning reducing the number of required training samples by a factor of 3--10. This has theoretical implications in terms of understanding emotion and mechanisms that may cast light on related phenomena such as creativity and serendipity. It also has potential practical applications in improving machine leaning and maybe even alleviating dysfunctional regret. Conference Paper/Proceeding/Abstract CIFMA 2021, Software Engineering and Formal Methods. SEFM 2021 Collocated Workshops 13230 Springer Regret Cognitive modelEmotionMachine learningHuman-Computer Interaction 0 0 0 0001-01-01 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University Not Required 2022-07-28T07:26:32.3063977 2022-04-12T19:36:10.5027749 College of Science Computer Science Alan Dix 0000-0002-5242-7693 1 Genovefa Kefalidou 0000-0002-2889-7564 2
title Regret from cognition to code
spellingShingle Regret from cognition to code
Alan Dix
title_short Regret from cognition to code
title_full Regret from cognition to code
title_fullStr Regret from cognition to code
title_full_unstemmed Regret from cognition to code
title_sort Regret from cognition to code
author_id_str_mv e31e47c578b2a6a39949aa7f149f4cf9
author_id_fullname_str_mv e31e47c578b2a6a39949aa7f149f4cf9_***_Alan Dix
author Alan Dix
author2 Alan Dix
Genovefa Kefalidou
format Conference Paper/Proceeding/Abstract
container_title CIFMA 2021, Software Engineering and Formal Methods. SEFM 2021 Collocated Workshops
container_volume 13230
institution Swansea University
publisher Springer
college_str College of Science
hierarchytype
hierarchy_top_id collegeofscience
hierarchy_top_title College of Science
hierarchy_parent_id collegeofscience
hierarchy_parent_title College of Science
department_str Computer Science{{{_:::_}}}College of Science{{{_:::_}}}Computer Science
document_store_str 0
active_str 0
description Regret seems like a very negative emotion, sometimes even debilitating. However, emotions usually have a purpose -- in the case of regret to help us learn from past mistakes. In this paper we first present an informal cognitive account of the way regret is built from a wide range of both primitive and more sophisticated mental abilities. The story includes Skinner-level learning, imagination, emotion, and counter-factual reasoning. When it works well this system focuses attention on aspects of past events where a small difference in behaviour would have made a big difference in outcome -- precisely the most important lessons to learn. The paper then takes elements of this cognitive account and creates a computational model, which can be applied in simple learning situations. We find that even this simplified model boosts machine learning reducing the number of required training samples by a factor of 3--10. This has theoretical implications in terms of understanding emotion and mechanisms that may cast light on related phenomena such as creativity and serendipity. It also has potential practical applications in improving machine leaning and maybe even alleviating dysfunctional regret.
published_date 0001-01-01T07:26:31Z
_version_ 1739576670101176320
score 10.888095