An unsupervised generative strategy for detection and characterization of rare behavioural events in mice in open fiel to assess effect of optogenetic activation of serotonergic neurons in the dorsal raphe nuclei
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10451/40873 |
Resumo: | The purpose of our work is to provide an unsupervised deep learning tool that uses predictability of behavior as a meaningful metric to quantify the di erences between normal and abnormal behavior in the context of an experiment where mice receive optogenetic stimulation in their serotonergic neurons located in the dorsal raphe nuclei. We use generative adversarial networks to learn, on a training subset of the videos, a baseline behavioral repertoire by predicting future frames from subsequent frames in the past. By de ning a predictability index as dissimilarity between the quality of the generated prediction and the ground truth frame, we are able to determine in which frames a behavior not observed by the model during training is performed and therefore, we can detect the presence of stimulation by only analysing the uctuations of this index that indicate when the mouse is performing behaviors that are not present in the learnt baseline. |
id |
RCAP_b21599d2a9b7d07f67636c365bbc0470 |
---|---|
oai_identifier_str |
oai:repositorio.ul.pt:10451/40873 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
An unsupervised generative strategy for detection and characterization of rare behavioural events in mice in open fiel to assess effect of optogenetic activation of serotonergic neurons in the dorsal raphe nucleiRedes neurais (Fisiologia)Aprendizagem automáticaControlo electrónico do comportamentoSerotoninaInteligência artificialTeses de mestrado - 2019Domínio/Área Científica::Ciências Sociais::PsicologiaDomínio/Área Científica::Ciências MédicasThe purpose of our work is to provide an unsupervised deep learning tool that uses predictability of behavior as a meaningful metric to quantify the di erences between normal and abnormal behavior in the context of an experiment where mice receive optogenetic stimulation in their serotonergic neurons located in the dorsal raphe nuclei. We use generative adversarial networks to learn, on a training subset of the videos, a baseline behavioral repertoire by predicting future frames from subsequent frames in the past. By de ning a predictability index as dissimilarity between the quality of the generated prediction and the ground truth frame, we are able to determine in which frames a behavior not observed by the model during training is performed and therefore, we can detect the presence of stimulation by only analysing the uctuations of this index that indicate when the mouse is performing behaviors that are not present in the learnt baseline.O objetivo do presente trabalho é fornecer uma ferramenta de aprendizado profundo que utiliza a previsibilidade do comportamento animal como uma métrica para quanti car as diferenças entre o comportamento normal e anormal no contexto de um experimento em que os ratos recebem estimulação optogenética em seus neurónios serotoninérgicos localizados na região cerebral do núcleo dorsal da rafe. Usamos redes neurais generativas para aprender, treinando em segmentos de vídeo, um repertório comportamental básico, prevendo cenas futuras a partir de cenas subsequentes do passado. Ao defi nir um índice de previsibilidade como o grau de dissimilaridade entre a previsão gerada pelo modelo e a cena real no momento correspondente, conseguimos determinar em quais cenas o comportamento não observado pelo modelo durante o treinamento é realizado e, portanto, pudemos detectar a presença de estimulação apenas analisando as flutuações desse índice que indicam quando o rato está executando comportamentos que não estão presentes na base aprendida.Mainen, Zachary FCorreia, LuísRepositório da Universidade de LisboaSoares, Lucas B. Nicolosi2020-01-16T14:12:15Z2019-10-232019-09-052019-10-23T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10451/40873TID:202329895enginfo: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:RCAAP2023-11-08T16:40:31Zoai:repositorio.ul.pt:10451/40873Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T21:54:31.800637Repositório 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 |
An unsupervised generative strategy for detection and characterization of rare behavioural events in mice in open fiel to assess effect of optogenetic activation of serotonergic neurons in the dorsal raphe nuclei |
title |
An unsupervised generative strategy for detection and characterization of rare behavioural events in mice in open fiel to assess effect of optogenetic activation of serotonergic neurons in the dorsal raphe nuclei |
spellingShingle |
An unsupervised generative strategy for detection and characterization of rare behavioural events in mice in open fiel to assess effect of optogenetic activation of serotonergic neurons in the dorsal raphe nuclei Soares, Lucas B. Nicolosi Redes neurais (Fisiologia) Aprendizagem automática Controlo electrónico do comportamento Serotonina Inteligência artificial Teses de mestrado - 2019 Domínio/Área Científica::Ciências Sociais::Psicologia Domínio/Área Científica::Ciências Médicas |
title_short |
An unsupervised generative strategy for detection and characterization of rare behavioural events in mice in open fiel to assess effect of optogenetic activation of serotonergic neurons in the dorsal raphe nuclei |
title_full |
An unsupervised generative strategy for detection and characterization of rare behavioural events in mice in open fiel to assess effect of optogenetic activation of serotonergic neurons in the dorsal raphe nuclei |
title_fullStr |
An unsupervised generative strategy for detection and characterization of rare behavioural events in mice in open fiel to assess effect of optogenetic activation of serotonergic neurons in the dorsal raphe nuclei |
title_full_unstemmed |
An unsupervised generative strategy for detection and characterization of rare behavioural events in mice in open fiel to assess effect of optogenetic activation of serotonergic neurons in the dorsal raphe nuclei |
title_sort |
An unsupervised generative strategy for detection and characterization of rare behavioural events in mice in open fiel to assess effect of optogenetic activation of serotonergic neurons in the dorsal raphe nuclei |
author |
Soares, Lucas B. Nicolosi |
author_facet |
Soares, Lucas B. Nicolosi |
author_role |
author |
dc.contributor.none.fl_str_mv |
Mainen, Zachary F Correia, Luís Repositório da Universidade de Lisboa |
dc.contributor.author.fl_str_mv |
Soares, Lucas B. Nicolosi |
dc.subject.por.fl_str_mv |
Redes neurais (Fisiologia) Aprendizagem automática Controlo electrónico do comportamento Serotonina Inteligência artificial Teses de mestrado - 2019 Domínio/Área Científica::Ciências Sociais::Psicologia Domínio/Área Científica::Ciências Médicas |
topic |
Redes neurais (Fisiologia) Aprendizagem automática Controlo electrónico do comportamento Serotonina Inteligência artificial Teses de mestrado - 2019 Domínio/Área Científica::Ciências Sociais::Psicologia Domínio/Área Científica::Ciências Médicas |
description |
The purpose of our work is to provide an unsupervised deep learning tool that uses predictability of behavior as a meaningful metric to quantify the di erences between normal and abnormal behavior in the context of an experiment where mice receive optogenetic stimulation in their serotonergic neurons located in the dorsal raphe nuclei. We use generative adversarial networks to learn, on a training subset of the videos, a baseline behavioral repertoire by predicting future frames from subsequent frames in the past. By de ning a predictability index as dissimilarity between the quality of the generated prediction and the ground truth frame, we are able to determine in which frames a behavior not observed by the model during training is performed and therefore, we can detect the presence of stimulation by only analysing the uctuations of this index that indicate when the mouse is performing behaviors that are not present in the learnt baseline. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-10-23 2019-09-05 2019-10-23T00:00:00Z 2020-01-16T14:12:15Z |
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/10451/40873 TID:202329895 |
url |
http://hdl.handle.net/10451/40873 |
identifier_str_mv |
TID:202329895 |
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_ |
1799134484662059008 |