Extracting Ontologies From Neural Networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10362/151092 |
Resumo: | Artificial neural network-based methods have been growing in popularity, being success- fully applied to perform a variety of tasks. As these systems begin to be deployed in domains where it is desired that they have a certain degree of autonomy and respon- sibility, the need to comprehend the reasoning behind their answers is becoming a re- quirement. Though, neural networks are still regarded as black boxes, since their internal representation do not provide any human-understandable explanation for their outputs. A considerable amount of work has been done towards the development of methods to increase the interpretability of neural networks. However, these methods often produce interpretations are too complex and do not have any declarative meaning, leaving the user with the burden of rationalizing them. Recent work has shown that it is possible to establish mappings between a neural network’s internal representations and a set of human-understandable concepts. In this dissertation we propose a method that leverage these mappings to induce an ontology that describes a neural network’s classification process, through logical relations between human-understandable concepts. |
id |
RCAP_a9028b93ea32b94decf96352cc8c6a7e |
---|---|
oai_identifier_str |
oai:run.unl.pt:10362/151092 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Extracting Ontologies From Neural NetworksArtificial Neural NetworksOntologiesRule ExtractionInductive Logic ProgrammingDomínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e InformáticaArtificial neural network-based methods have been growing in popularity, being success- fully applied to perform a variety of tasks. As these systems begin to be deployed in domains where it is desired that they have a certain degree of autonomy and respon- sibility, the need to comprehend the reasoning behind their answers is becoming a re- quirement. Though, neural networks are still regarded as black boxes, since their internal representation do not provide any human-understandable explanation for their outputs. A considerable amount of work has been done towards the development of methods to increase the interpretability of neural networks. However, these methods often produce interpretations are too complex and do not have any declarative meaning, leaving the user with the burden of rationalizing them. Recent work has shown that it is possible to establish mappings between a neural network’s internal representations and a set of human-understandable concepts. In this dissertation we propose a method that leverage these mappings to induce an ontology that describes a neural network’s classification process, through logical relations between human-understandable concepts.Métodos com base em redes neuronais artificiais têm ganho cada vez mais popularidade, e têm sido aplicados na resolução das mais variadas tarefas. À medida que estes sistemas são usados em domínios onde se pretende que tenham um determinado grau de auto- nomia e responsabilidade, a necessidade de compreender o raciocínio que os conduz às suas respostas torna-se indispensável. No entanto, as redes neuronais são vistas como caixas negras, dado que as suas representações internas não constituem uma explicação interpretável para os seus resultados. Tem sido realizada uma quantidade considerável de investigação com o objetivo de desenvolver métodos que permitam o aumento da interpretabilidade de redes neuronais. Todavia, estes métodos tendem a produzir inter- pretações complexas e a que não possuem nenhum significado declarativo, deixando o utilizador com a responsabilidade as racionalizar. Uma publicação recente mostrou que é possível estabelecer mapeamentos entre as representações internas de uma rede neuronal e conceitos interpretáveis. Nesta dissertação propomos um método que faz uso destes mapeamentos para induzir uma ontologia que reflete o processo de classificação de uma rede neuronal, através de conceitos compreensiveis relacionados logicamente.Leite, JoãoGonçalves, RicardoRUNFerreira, João Miguel Dias2023-03-23T09:17:51Z2022-112022-11-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/151092enginfo: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:RCAAP2024-03-11T05:33:33Zoai:run.unl.pt:10362/151092Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:54:27.801950Repositório 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 |
Extracting Ontologies From Neural Networks |
title |
Extracting Ontologies From Neural Networks |
spellingShingle |
Extracting Ontologies From Neural Networks Ferreira, João Miguel Dias Artificial Neural Networks Ontologies Rule Extraction Inductive Logic Programming Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
title_short |
Extracting Ontologies From Neural Networks |
title_full |
Extracting Ontologies From Neural Networks |
title_fullStr |
Extracting Ontologies From Neural Networks |
title_full_unstemmed |
Extracting Ontologies From Neural Networks |
title_sort |
Extracting Ontologies From Neural Networks |
author |
Ferreira, João Miguel Dias |
author_facet |
Ferreira, João Miguel Dias |
author_role |
author |
dc.contributor.none.fl_str_mv |
Leite, João Gonçalves, Ricardo RUN |
dc.contributor.author.fl_str_mv |
Ferreira, João Miguel Dias |
dc.subject.por.fl_str_mv |
Artificial Neural Networks Ontologies Rule Extraction Inductive Logic Programming Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
topic |
Artificial Neural Networks Ontologies Rule Extraction Inductive Logic Programming Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática |
description |
Artificial neural network-based methods have been growing in popularity, being success- fully applied to perform a variety of tasks. As these systems begin to be deployed in domains where it is desired that they have a certain degree of autonomy and respon- sibility, the need to comprehend the reasoning behind their answers is becoming a re- quirement. Though, neural networks are still regarded as black boxes, since their internal representation do not provide any human-understandable explanation for their outputs. A considerable amount of work has been done towards the development of methods to increase the interpretability of neural networks. However, these methods often produce interpretations are too complex and do not have any declarative meaning, leaving the user with the burden of rationalizing them. Recent work has shown that it is possible to establish mappings between a neural network’s internal representations and a set of human-understandable concepts. In this dissertation we propose a method that leverage these mappings to induce an ontology that describes a neural network’s classification process, through logical relations between human-understandable concepts. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-11 2022-11-01T00:00:00Z 2023-03-23T09:17:51Z |
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/10362/151092 |
url |
http://hdl.handle.net/10362/151092 |
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_ |
1799138133097316352 |