Exploring Geometric Feature Hyper-Space in Data to Learn Representations of Abstract Concepts

Detalhes bibliográficos
Autor(a) principal: Sharma, Rahul
Data de Publicação: 2020
Outros Autores: Ribeiro, Bernardete, Miguel Pinto, Alexandre, Cardoso, F. Amílcar
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10316/105797
https://doi.org/10.3390/app10061994
Resumo: The term concept has been a prominent part of investigations in psychology and neurobiology where, mostly, it is mathematically or theoretically represented. Concepts are also studied in the computational domain through their symbolic, distributed and hybrid representations. The majority of these approaches focused on addressing concrete concepts notion, but the view of the abstract concept is rarely explored. Moreover, most computational approaches have a predefined structure or configurations. The proposed method, Regulated Activation Network (RAN), has an evolving topology and learns representations of abstract concepts by exploiting the geometrical view of concepts, without supervision. In the article, first, a Toy-data problem was used to demonstrate the RANs modeling. Secondly, we demonstrate the liberty of concept identifier choice in RANs modeling and deep hierarchy generation using the IRIS dataset. Thirdly, data from the IoT’s human activity recognition problem is used to show automatic identification of alike classes as abstract concepts. The evaluation of RAN with eight UCI benchmarks and the comparisons with fiveMachine Learning models establishes the RANs credibility as a classifier. The classification operation also proved the RANs hypothesis of abstract concept representation. The experiments demonstrate the RANs ability to simulate psychological processes (like concept creation and learning) and carry out effective classification irrespective of training data size.
id RCAP_ed2f66af992f69f51c1542f1df443c96
oai_identifier_str oai:estudogeral.uc.pt:10316/105797
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Exploring Geometric Feature Hyper-Space in Data to Learn Representations of Abstract Conceptsunsupervised machine learninghierarchical learningcomputational representationcomputational cognitive modelingcontextual modelingclassificationIoT data modelingThe term concept has been a prominent part of investigations in psychology and neurobiology where, mostly, it is mathematically or theoretically represented. Concepts are also studied in the computational domain through their symbolic, distributed and hybrid representations. The majority of these approaches focused on addressing concrete concepts notion, but the view of the abstract concept is rarely explored. Moreover, most computational approaches have a predefined structure or configurations. The proposed method, Regulated Activation Network (RAN), has an evolving topology and learns representations of abstract concepts by exploiting the geometrical view of concepts, without supervision. In the article, first, a Toy-data problem was used to demonstrate the RANs modeling. Secondly, we demonstrate the liberty of concept identifier choice in RANs modeling and deep hierarchy generation using the IRIS dataset. Thirdly, data from the IoT’s human activity recognition problem is used to show automatic identification of alike classes as abstract concepts. The evaluation of RAN with eight UCI benchmarks and the comparisons with fiveMachine Learning models establishes the RANs credibility as a classifier. The classification operation also proved the RANs hypothesis of abstract concept representation. The experiments demonstrate the RANs ability to simulate psychological processes (like concept creation and learning) and carry out effective classification irrespective of training data size.MDPI2020info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10316/105797http://hdl.handle.net/10316/105797https://doi.org/10.3390/app10061994eng2076-3417Sharma, RahulRibeiro, BernardeteMiguel Pinto, AlexandreCardoso, F. Amílcarinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-03-08T21:31:20Zoai:estudogeral.uc.pt:10316/105797Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T21:22:17.955469Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Exploring Geometric Feature Hyper-Space in Data to Learn Representations of Abstract Concepts
title Exploring Geometric Feature Hyper-Space in Data to Learn Representations of Abstract Concepts
spellingShingle Exploring Geometric Feature Hyper-Space in Data to Learn Representations of Abstract Concepts
Sharma, Rahul
unsupervised machine learning
hierarchical learning
computational representation
computational cognitive modeling
contextual modeling
classification
IoT data modeling
title_short Exploring Geometric Feature Hyper-Space in Data to Learn Representations of Abstract Concepts
title_full Exploring Geometric Feature Hyper-Space in Data to Learn Representations of Abstract Concepts
title_fullStr Exploring Geometric Feature Hyper-Space in Data to Learn Representations of Abstract Concepts
title_full_unstemmed Exploring Geometric Feature Hyper-Space in Data to Learn Representations of Abstract Concepts
title_sort Exploring Geometric Feature Hyper-Space in Data to Learn Representations of Abstract Concepts
author Sharma, Rahul
author_facet Sharma, Rahul
Ribeiro, Bernardete
Miguel Pinto, Alexandre
Cardoso, F. Amílcar
author_role author
author2 Ribeiro, Bernardete
Miguel Pinto, Alexandre
Cardoso, F. Amílcar
author2_role author
author
author
dc.contributor.author.fl_str_mv Sharma, Rahul
Ribeiro, Bernardete
Miguel Pinto, Alexandre
Cardoso, F. Amílcar
dc.subject.por.fl_str_mv unsupervised machine learning
hierarchical learning
computational representation
computational cognitive modeling
contextual modeling
classification
IoT data modeling
topic unsupervised machine learning
hierarchical learning
computational representation
computational cognitive modeling
contextual modeling
classification
IoT data modeling
description The term concept has been a prominent part of investigations in psychology and neurobiology where, mostly, it is mathematically or theoretically represented. Concepts are also studied in the computational domain through their symbolic, distributed and hybrid representations. The majority of these approaches focused on addressing concrete concepts notion, but the view of the abstract concept is rarely explored. Moreover, most computational approaches have a predefined structure or configurations. The proposed method, Regulated Activation Network (RAN), has an evolving topology and learns representations of abstract concepts by exploiting the geometrical view of concepts, without supervision. In the article, first, a Toy-data problem was used to demonstrate the RANs modeling. Secondly, we demonstrate the liberty of concept identifier choice in RANs modeling and deep hierarchy generation using the IRIS dataset. Thirdly, data from the IoT’s human activity recognition problem is used to show automatic identification of alike classes as abstract concepts. The evaluation of RAN with eight UCI benchmarks and the comparisons with fiveMachine Learning models establishes the RANs credibility as a classifier. The classification operation also proved the RANs hypothesis of abstract concept representation. The experiments demonstrate the RANs ability to simulate psychological processes (like concept creation and learning) and carry out effective classification irrespective of training data size.
publishDate 2020
dc.date.none.fl_str_mv 2020
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10316/105797
http://hdl.handle.net/10316/105797
https://doi.org/10.3390/app10061994
url http://hdl.handle.net/10316/105797
https://doi.org/10.3390/app10061994
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2076-3417
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799134112737394688