Neural and Symbolic AI - mind the gap! Aligning Artificial Neural Networks and Ontologies
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10362/113651 |
Resumo: | Artificial neural networks have been the key to solve a variety of different problems. However, neural network models are still essentially regarded as black boxes, since they do not provide any human-interpretable evidence as to why they output a certain re sult. In this dissertation, we address this issue by leveraging on ontologies and building small classifiers that map a neural network’s internal representations to concepts from an ontology, enabling the generation of symbolic justifications for the output of neural networks. Using two image classification problems as testing ground, we discuss how to map the internal representations of a neural network to the concepts of an ontology, exam ine whether the results obtained by the established mappings match our understanding of the mapped concepts, and analyze the justifications obtained through this method. |
id |
RCAP_1d1f80bffc2bf724ea58de9025f855f2 |
---|---|
oai_identifier_str |
oai:run.unl.pt:10362/113651 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Neural and Symbolic AI - mind the gap! Aligning Artificial Neural Networks and Ontologiesartificial intelligenceneural networksontologiesexplainable AIDomínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e InformáticaArtificial neural networks have been the key to solve a variety of different problems. However, neural network models are still essentially regarded as black boxes, since they do not provide any human-interpretable evidence as to why they output a certain re sult. In this dissertation, we address this issue by leveraging on ontologies and building small classifiers that map a neural network’s internal representations to concepts from an ontology, enabling the generation of symbolic justifications for the output of neural networks. Using two image classification problems as testing ground, we discuss how to map the internal representations of a neural network to the concepts of an ontology, exam ine whether the results obtained by the established mappings match our understanding of the mapped concepts, and analyze the justifications obtained through this method.Leite, JoãoRUNRibeiro, Manuel António de Melo Chinopa de Sousa2021-03-10T23:04:41Z2021-0120202021-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/113651enginfo: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:RCAAP2024-03-11T04:56:34Zoai:run.unl.pt:10362/113651Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:42:21.462679Repositório 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 |
Neural and Symbolic AI - mind the gap! Aligning Artificial Neural Networks and Ontologies |
title |
Neural and Symbolic AI - mind the gap! Aligning Artificial Neural Networks and Ontologies |
spellingShingle |
Neural and Symbolic AI - mind the gap! Aligning Artificial Neural Networks and Ontologies Ribeiro, Manuel António de Melo Chinopa de Sousa artificial intelligence neural networks ontologies explainable AI Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
title_short |
Neural and Symbolic AI - mind the gap! Aligning Artificial Neural Networks and Ontologies |
title_full |
Neural and Symbolic AI - mind the gap! Aligning Artificial Neural Networks and Ontologies |
title_fullStr |
Neural and Symbolic AI - mind the gap! Aligning Artificial Neural Networks and Ontologies |
title_full_unstemmed |
Neural and Symbolic AI - mind the gap! Aligning Artificial Neural Networks and Ontologies |
title_sort |
Neural and Symbolic AI - mind the gap! Aligning Artificial Neural Networks and Ontologies |
author |
Ribeiro, Manuel António de Melo Chinopa de Sousa |
author_facet |
Ribeiro, Manuel António de Melo Chinopa de Sousa |
author_role |
author |
dc.contributor.none.fl_str_mv |
Leite, João RUN |
dc.contributor.author.fl_str_mv |
Ribeiro, Manuel António de Melo Chinopa de Sousa |
dc.subject.por.fl_str_mv |
artificial intelligence neural networks ontologies explainable AI Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
topic |
artificial intelligence neural networks ontologies explainable AI Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
description |
Artificial neural networks have been the key to solve a variety of different problems. However, neural network models are still essentially regarded as black boxes, since they do not provide any human-interpretable evidence as to why they output a certain re sult. In this dissertation, we address this issue by leveraging on ontologies and building small classifiers that map a neural network’s internal representations to concepts from an ontology, enabling the generation of symbolic justifications for the output of neural networks. Using two image classification problems as testing ground, we discuss how to map the internal representations of a neural network to the concepts of an ontology, exam ine whether the results obtained by the established mappings match our understanding of the mapped concepts, and analyze the justifications obtained through this method. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020 2021-03-10T23:04:41Z 2021-01 2021-01-01T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10362/113651 |
url |
http://hdl.handle.net/10362/113651 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
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_ |
1799138035085869056 |