Loading…
From conceptual spaces to quantum concepts: formalising and learning structured conceptual models
In this article we present a new modelling framework for structured concepts using a category-theoretic generalisation of conceptual spaces, and show how the conceptual representations can be learned automatically from data, using two very different instantiations: one classical and one quantum. A c...
Saved in:
Published in: | Quantum machine intelligence 2024-06, Vol.6 (1), Article 21 |
---|---|
Main Authors: | , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | |
---|---|
cites | cdi_FETCH-LOGICAL-c242t-da12fccb819ecc28ca0891035dbf125aa46b32815a1af11b4924240ec8f0c04b3 |
container_end_page | |
container_issue | 1 |
container_start_page | |
container_title | Quantum machine intelligence |
container_volume | 6 |
creator | Tull, Sean Shaikh, Razin A. Zemljič, Sara Sabrina Clark, Stephen |
description | In this article we present a new modelling framework for structured concepts using a category-theoretic generalisation of conceptual spaces, and show how the conceptual representations can be learned automatically from data, using two very different instantiations: one classical and one quantum. A contribution of the work is a thorough category-theoretic formalisation of our framework. We claim that the use of category theory, and in particular the use of string diagrams to describe quantum processes, helps elucidate some of the most important features of our approach. We build upon Gärdenfors’ classical framework of
conceptual spaces
, in which cognition is modelled geometrically through the use of convex spaces, which in turn factorise in terms of simpler spaces called
domains
. We show how concepts from the domains of
shape
,
colour
,
size
and
position
can be learned from images of simple shapes, where concepts are represented as Gaussians in the classical implementation, and quantum effects in the quantum one. In the classical case we develop a new model which is inspired by the
β
-VAE model of concepts, but is designed to be more closely connected with language, so that the names of concepts form part of the graphical model. In the quantum case, concepts are learned by a hybrid classical-quantum network trained to perform concept classification, where the classical image processing is carried out by a convolutional neural network and the quantum representations are produced by a parameterised quantum circuit. Finally, we consider the question of whether our quantum models of concepts can be considered conceptual spaces in the Gärdenfors sense. |
doi_str_mv | 10.1007/s42484-023-00134-z |
format | article |
fullrecord | <record><control><sourceid>crossref_sprin</sourceid><recordid>TN_cdi_crossref_primary_10_1007_s42484_023_00134_z</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1007_s42484_023_00134_z</sourcerecordid><originalsourceid>FETCH-LOGICAL-c242t-da12fccb819ecc28ca0891035dbf125aa46b32815a1af11b4924240ec8f0c04b3</originalsourceid><addsrcrecordid>eNp9kM9OwzAMhyMEEtPYC3DKCwScP91SbmhigDSJC5wjN02mTW1SkvbAnp6OookTJ9uyv5-sj5BbDnccYHWflVBaMRCSAXCp2PGCzEQhFFMlV5fnHpbXZJHzAQDESioNyxnBTYottTFY1_UDNjR3aF2mfaSfA4Z-OC_zA_Uxtdjs8z7sKIaaNg5TOA25T4Pth-Tqv1FtrF2Tb8iVxya7xW-dk4_N0_v6hW3fnl_Xj1tmhRI9q5ELb22leemsFdoi6JKDLOrKc1EgqmUlheYFcvScV6ocMQXOag8WVCXnREy5NsWck_OmS_sW05fhYE6ezOTJjJ7MjydzHCE5QXk8DjuXzCEOKYx__kd9A5uzbiU</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>From conceptual spaces to quantum concepts: formalising and learning structured conceptual models</title><source>Springer Nature</source><creator>Tull, Sean ; Shaikh, Razin A. ; Zemljič, Sara Sabrina ; Clark, Stephen</creator><creatorcontrib>Tull, Sean ; Shaikh, Razin A. ; Zemljič, Sara Sabrina ; Clark, Stephen</creatorcontrib><description>In this article we present a new modelling framework for structured concepts using a category-theoretic generalisation of conceptual spaces, and show how the conceptual representations can be learned automatically from data, using two very different instantiations: one classical and one quantum. A contribution of the work is a thorough category-theoretic formalisation of our framework. We claim that the use of category theory, and in particular the use of string diagrams to describe quantum processes, helps elucidate some of the most important features of our approach. We build upon Gärdenfors’ classical framework of
conceptual spaces
, in which cognition is modelled geometrically through the use of convex spaces, which in turn factorise in terms of simpler spaces called
domains
. We show how concepts from the domains of
shape
,
colour
,
size
and
position
can be learned from images of simple shapes, where concepts are represented as Gaussians in the classical implementation, and quantum effects in the quantum one. In the classical case we develop a new model which is inspired by the
β
-VAE model of concepts, but is designed to be more closely connected with language, so that the names of concepts form part of the graphical model. In the quantum case, concepts are learned by a hybrid classical-quantum network trained to perform concept classification, where the classical image processing is carried out by a convolutional neural network and the quantum representations are produced by a parameterised quantum circuit. Finally, we consider the question of whether our quantum models of concepts can be considered conceptual spaces in the Gärdenfors sense.</description><identifier>ISSN: 2524-4906</identifier><identifier>EISSN: 2524-4914</identifier><identifier>DOI: 10.1007/s42484-023-00134-z</identifier><language>eng</language><publisher>Cham: Springer International Publishing</publisher><subject>Artificial Intelligence ; Computational Intelligence ; Engineering ; Quantum Information Technology ; Research Article ; Spintronics</subject><ispartof>Quantum machine intelligence, 2024-06, Vol.6 (1), Article 21</ispartof><rights>The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c242t-da12fccb819ecc28ca0891035dbf125aa46b32815a1af11b4924240ec8f0c04b3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,777,781,27905,27906</link.rule.ids></links><search><creatorcontrib>Tull, Sean</creatorcontrib><creatorcontrib>Shaikh, Razin A.</creatorcontrib><creatorcontrib>Zemljič, Sara Sabrina</creatorcontrib><creatorcontrib>Clark, Stephen</creatorcontrib><title>From conceptual spaces to quantum concepts: formalising and learning structured conceptual models</title><title>Quantum machine intelligence</title><addtitle>Quantum Mach. Intell</addtitle><description>In this article we present a new modelling framework for structured concepts using a category-theoretic generalisation of conceptual spaces, and show how the conceptual representations can be learned automatically from data, using two very different instantiations: one classical and one quantum. A contribution of the work is a thorough category-theoretic formalisation of our framework. We claim that the use of category theory, and in particular the use of string diagrams to describe quantum processes, helps elucidate some of the most important features of our approach. We build upon Gärdenfors’ classical framework of
conceptual spaces
, in which cognition is modelled geometrically through the use of convex spaces, which in turn factorise in terms of simpler spaces called
domains
. We show how concepts from the domains of
shape
,
colour
,
size
and
position
can be learned from images of simple shapes, where concepts are represented as Gaussians in the classical implementation, and quantum effects in the quantum one. In the classical case we develop a new model which is inspired by the
β
-VAE model of concepts, but is designed to be more closely connected with language, so that the names of concepts form part of the graphical model. In the quantum case, concepts are learned by a hybrid classical-quantum network trained to perform concept classification, where the classical image processing is carried out by a convolutional neural network and the quantum representations are produced by a parameterised quantum circuit. Finally, we consider the question of whether our quantum models of concepts can be considered conceptual spaces in the Gärdenfors sense.</description><subject>Artificial Intelligence</subject><subject>Computational Intelligence</subject><subject>Engineering</subject><subject>Quantum Information Technology</subject><subject>Research Article</subject><subject>Spintronics</subject><issn>2524-4906</issn><issn>2524-4914</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNp9kM9OwzAMhyMEEtPYC3DKCwScP91SbmhigDSJC5wjN02mTW1SkvbAnp6OookTJ9uyv5-sj5BbDnccYHWflVBaMRCSAXCp2PGCzEQhFFMlV5fnHpbXZJHzAQDESioNyxnBTYottTFY1_UDNjR3aF2mfaSfA4Z-OC_zA_Uxtdjs8z7sKIaaNg5TOA25T4Pth-Tqv1FtrF2Tb8iVxya7xW-dk4_N0_v6hW3fnl_Xj1tmhRI9q5ELb22leemsFdoi6JKDLOrKc1EgqmUlheYFcvScV6ocMQXOag8WVCXnREy5NsWck_OmS_sW05fhYE6ezOTJjJ7MjydzHCE5QXk8DjuXzCEOKYx__kd9A5uzbiU</recordid><startdate>20240601</startdate><enddate>20240601</enddate><creator>Tull, Sean</creator><creator>Shaikh, Razin A.</creator><creator>Zemljič, Sara Sabrina</creator><creator>Clark, Stephen</creator><general>Springer International Publishing</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20240601</creationdate><title>From conceptual spaces to quantum concepts: formalising and learning structured conceptual models</title><author>Tull, Sean ; Shaikh, Razin A. ; Zemljič, Sara Sabrina ; Clark, Stephen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c242t-da12fccb819ecc28ca0891035dbf125aa46b32815a1af11b4924240ec8f0c04b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Artificial Intelligence</topic><topic>Computational Intelligence</topic><topic>Engineering</topic><topic>Quantum Information Technology</topic><topic>Research Article</topic><topic>Spintronics</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tull, Sean</creatorcontrib><creatorcontrib>Shaikh, Razin A.</creatorcontrib><creatorcontrib>Zemljič, Sara Sabrina</creatorcontrib><creatorcontrib>Clark, Stephen</creatorcontrib><collection>CrossRef</collection><jtitle>Quantum machine intelligence</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tull, Sean</au><au>Shaikh, Razin A.</au><au>Zemljič, Sara Sabrina</au><au>Clark, Stephen</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>From conceptual spaces to quantum concepts: formalising and learning structured conceptual models</atitle><jtitle>Quantum machine intelligence</jtitle><stitle>Quantum Mach. Intell</stitle><date>2024-06-01</date><risdate>2024</risdate><volume>6</volume><issue>1</issue><artnum>21</artnum><issn>2524-4906</issn><eissn>2524-4914</eissn><abstract>In this article we present a new modelling framework for structured concepts using a category-theoretic generalisation of conceptual spaces, and show how the conceptual representations can be learned automatically from data, using two very different instantiations: one classical and one quantum. A contribution of the work is a thorough category-theoretic formalisation of our framework. We claim that the use of category theory, and in particular the use of string diagrams to describe quantum processes, helps elucidate some of the most important features of our approach. We build upon Gärdenfors’ classical framework of
conceptual spaces
, in which cognition is modelled geometrically through the use of convex spaces, which in turn factorise in terms of simpler spaces called
domains
. We show how concepts from the domains of
shape
,
colour
,
size
and
position
can be learned from images of simple shapes, where concepts are represented as Gaussians in the classical implementation, and quantum effects in the quantum one. In the classical case we develop a new model which is inspired by the
β
-VAE model of concepts, but is designed to be more closely connected with language, so that the names of concepts form part of the graphical model. In the quantum case, concepts are learned by a hybrid classical-quantum network trained to perform concept classification, where the classical image processing is carried out by a convolutional neural network and the quantum representations are produced by a parameterised quantum circuit. Finally, we consider the question of whether our quantum models of concepts can be considered conceptual spaces in the Gärdenfors sense.</abstract><cop>Cham</cop><pub>Springer International Publishing</pub><doi>10.1007/s42484-023-00134-z</doi></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2524-4906 |
ispartof | Quantum machine intelligence, 2024-06, Vol.6 (1), Article 21 |
issn | 2524-4906 2524-4914 |
language | eng |
recordid | cdi_crossref_primary_10_1007_s42484_023_00134_z |
source | Springer Nature |
subjects | Artificial Intelligence Computational Intelligence Engineering Quantum Information Technology Research Article Spintronics |
title | From conceptual spaces to quantum concepts: formalising and learning structured conceptual models |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T16%3A58%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref_sprin&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=From%20conceptual%20spaces%20to%20quantum%20concepts:%20formalising%20and%20learning%20structured%20conceptual%20models&rft.jtitle=Quantum%20machine%20intelligence&rft.au=Tull,%20Sean&rft.date=2024-06-01&rft.volume=6&rft.issue=1&rft.artnum=21&rft.issn=2524-4906&rft.eissn=2524-4914&rft_id=info:doi/10.1007/s42484-023-00134-z&rft_dat=%3Ccrossref_sprin%3E10_1007_s42484_023_00134_z%3C/crossref_sprin%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c242t-da12fccb819ecc28ca0891035dbf125aa46b32815a1af11b4924240ec8f0c04b3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |