{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/113077"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/113077","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Decoding brains by paying attention: An attention-based fMRI task state decoding deep network architecture","abstract":"One of the core goals in the field of cognitive neuroscience is to decode task state fMRI data. Task decoding is the process of taking neuroimaging data and determining the task that was performed when that data was collected. A large volume of work used for task decoding is done in pursuit of creating a deep learning model for task prediction. Typically these models will include either handcrafted features or data driven approaches for downscaling the input features in successive layers. In this thesis, we explore and compare the effectiveness of linear, graph-based and attention-based methods for hierarchical classification. Furthermore, we propose a new attention-based network architecture which showcases superior performance to all of our baseline architectures without the use of handcrafted features on several neuroimaging datasets.","abstract_html":"One of the core goals in the field of cognitive neuroscience is to decode task state fMRI data. Task decoding is the process of taking neuroimaging data and determining the task that was performed when that data was collected. A large volume of work used for task decoding is done in pursuit of creating a deep learning model for task prediction. Typically these models will include either handcrafted features or data driven approaches for downscaling the input features in successive layers. In this thesis, we explore and compare the effectiveness of linear, graph-based and attention-based methods for hierarchical classification. Furthermore, we propose a new attention-based network architecture which showcases superior performance to all of our baseline architectures without the use of handcrafted features on several neuroimaging datasets.","abstract_has_math":false,"creators":["Roxas, Francis"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Koyejo, Oluwasanmi"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-01-12T21:46:56Z","date_published":"2022-01-12T21:46:56Z","updated_at":"2026-07-22T22:24:53Z","subjects":["Transformers, Graph Neural Networks, Graph Attention Networks, Attention, Machine Learning, Deep Learning, Brain Decoding"],"languages":["en"],"rights":["Copyright 2021 Francis Roxas"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/113077","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Koyejo, Oluwasanmi"]},{"key":"dc:creator","label":"Author","values":["Roxas, Francis"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-01-12T21:46:56Z","2021-07-20","2021-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Transformers, Graph Neural Networks, Graph Attention Networks, Attention, Machine Learning, Deep Learning, Brain Decoding"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2021 Francis Roxas"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/113077"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["One of the core goals in the field of cognitive neuroscience is to decode task state fMRI data. Task decoding is the process of taking neuroimaging data and determining the task that was performed when that data was collected. A large volume of work used for task decoding is done in pursuit of creating a deep learning model for task prediction. Typically these models will include either handcrafted features or data driven approaches for downscaling the input features in successive layers. In this thesis, we explore and compare the effectiveness of linear, graph-based and attention-based methods for hierarchical classification. Furthermore, we propose a new attention-based network architecture which showcases superior performance to all of our baseline architectures without the use of handcrafted features on several neuroimaging datasets.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-01-12 without embargo terms","The student, Francis Roxas, accepted the attached license on 2021-07-20 at 10:42.","The student, Francis Roxas, submitted this Thesis for approval on 2021-07-20 at 11:04.","This Thesis was approved for publication on 2021-07-20 at 13:26.","DSpace SAF Submission Ingestion Package generated from Vireo submission #17021 on 2022-01-12 at 12:46:22","Made available in DSpace on 2022-01-12T21:46:56Z (GMT). No. of bitstreams: 2 ROXAS-THESIS-2021.pdf: 2623592 bytes, checksum: c21fd90bc537c9fbabe209c516911a3e (MD5) LICENSE.txt: 4210 bytes, checksum: cc1486540e75836025cc039b10949493 (MD5) Previous issue date: 2021-07-20"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Decoding brains by paying attention: An attention-based fMRI task state decoding deep network architecture"]}]}],"canonical_facts":{"dc:contributor":["Koyejo, Oluwasanmi"],"dc:creator":["Roxas, Francis"],"dc:date":["2022-01-12T21:46:56Z","2021-07-20","2021-08"],"dc:description":["One of the core goals in the field of cognitive neuroscience is to decode task state fMRI data. Task decoding is the process of taking neuroimaging data and determining the task that was performed when that data was collected. A large volume of work used for task decoding is done in pursuit of creating a deep learning model for task prediction. Typically these models will include either handcrafted features or data driven approaches for downscaling the input features in successive layers. In this thesis, we explore and compare the effectiveness of linear, graph-based and attention-based methods for hierarchical classification. Furthermore, we propose a new attention-based network architecture which showcases superior performance to all of our baseline architectures without the use of handcrafted features on several neuroimaging datasets.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-01-12 without embargo terms","The student, Francis Roxas, accepted the attached license on 2021-07-20 at 10:42.","The student, Francis Roxas, submitted this Thesis for approval on 2021-07-20 at 11:04.","This Thesis was approved for publication on 2021-07-20 at 13:26.","DSpace SAF Submission Ingestion Package generated from Vireo submission #17021 on 2022-01-12 at 12:46:22","Made available in DSpace on 2022-01-12T21:46:56Z (GMT). No. of bitstreams: 2 ROXAS-THESIS-2021.pdf: 2623592 bytes, checksum: c21fd90bc537c9fbabe209c516911a3e (MD5) LICENSE.txt: 4210 bytes, checksum: cc1486540e75836025cc039b10949493 (MD5) Previous issue date: 2021-07-20"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/113077"],"dc:language":["en"],"dc:rights":["Copyright 2021 Francis Roxas"],"dc:subject":["Transformers, Graph Neural Networks, Graph Attention Networks, Attention, Machine Learning, Deep Learning, Brain Decoding"],"dc:title":["Decoding brains by paying attention: An attention-based fMRI task state decoding deep network architecture"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:53Z"}