{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/104898"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/104898","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"A spatial deep network architecture for brain decoding","abstract":"We propose the Fixed Grouping Layer (FGL); a novel feedforward layer designed to incorporate structured smoothness in a deep learning model. FGL achieves this goal by connecting nodes across layers based on spatial similarity. The inductive bias of structured smoothness implemented by FGL is motivated by applications such as brain image decoding, i.e., predicting behavior based on brain images, where scientific prior knowledge suggests that brain responses conditioned on behaviour are smoothed. Experimental results on simulated and real data is provided. Our proposed model architecture performs better than conventional neural network architectures.","abstract_html":"We propose the Fixed Grouping Layer (FGL); a novel feedforward layer designed to incorporate structured smoothness in a deep learning model. FGL achieves this goal by connecting nodes across layers based on spatial similarity. The inductive bias of structured smoothness implemented by FGL is motivated by applications such as brain image decoding, i.e., predicting behavior based on brain images, where scientific prior knowledge suggests that brain responses conditioned on behaviour are smoothed. Experimental results on simulated and real data is provided. Our proposed model architecture performs better than conventional neural network architectures.","abstract_has_math":false,"creators":["Habeeb, Haroun"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Koyejo, Oluwasanmi"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-08-23T20:00:11Z","date_published":"2019-08-23T20:00:11Z","updated_at":"2026-07-22T22:24:42Z","subjects":["Machine Learning","Brain Decoding","Deep Learning"],"languages":["en"],"rights":["Copyright 2019 Haroun Habeeb"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/104898","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":["Habeeb, Haroun"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-08-23T20:00:11Z","2019-04-22","2019-05"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"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":["Machine Learning","Brain Decoding","Deep Learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2019 Haroun Habeeb"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/104898"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["We propose the Fixed Grouping Layer (FGL); a novel feedforward layer designed to incorporate structured smoothness in a deep learning model. FGL achieves this goal by connecting nodes across layers based on spatial similarity. The inductive bias of structured smoothness implemented by FGL is motivated by applications such as brain image decoding, i.e., predicting behavior based on brain images, where scientific prior knowledge suggests that brain responses conditioned on behaviour are smoothed. Experimental results on simulated and real data is provided. Our proposed model architecture performs better than conventional neural network architectures.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2019-08-22 without embargo terms","The student, Haroun Habeeb, accepted the attached license on 2019-04-22 at 11:46.","The student, Haroun Habeeb, submitted this Thesis for approval on 2019-04-22 at 11:55.","This Thesis was approved for publication on 2019-04-22 at 14:25.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13818 on 2019-08-22 at 14:45:30","Made available in DSpace on 2019-08-23T20:00:11Z (GMT). No. of bitstreams: 3 HABEEB-THESIS-2019.pdf: 950178 bytes, checksum: b06d7a392d7eb491cd69e0e6e466245b (MD5) FGL_ Thesis.zip: 808566 bytes, checksum: 8722939dad64045ff8a9ffd6af43bd55 (MD5) LICENSE.txt: 4210 bytes, checksum: 0122c18517b3dd82bd6ce45e0307c717 (MD5) Previous issue date: 2019-04-22"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["A spatial deep network architecture for brain decoding"]}]}],"canonical_facts":{"dc:contributor":["Koyejo, Oluwasanmi"],"dc:creator":["Habeeb, Haroun"],"dc:date":["2019-08-23T20:00:11Z","2019-04-22","2019-05"],"dc:description":["We propose the Fixed Grouping Layer (FGL); a novel feedforward layer designed to incorporate structured smoothness in a deep learning model. FGL achieves this goal by connecting nodes across layers based on spatial similarity. The inductive bias of structured smoothness implemented by FGL is motivated by applications such as brain image decoding, i.e., predicting behavior based on brain images, where scientific prior knowledge suggests that brain responses conditioned on behaviour are smoothed. Experimental results on simulated and real data is provided. Our proposed model architecture performs better than conventional neural network architectures.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2019-08-22 without embargo terms","The student, Haroun Habeeb, accepted the attached license on 2019-04-22 at 11:46.","The student, Haroun Habeeb, submitted this Thesis for approval on 2019-04-22 at 11:55.","This Thesis was approved for publication on 2019-04-22 at 14:25.","DSpace SAF Submission Ingestion Package generated from Vireo submission #13818 on 2019-08-22 at 14:45:30","Made available in DSpace on 2019-08-23T20:00:11Z (GMT). No. of bitstreams: 3 HABEEB-THESIS-2019.pdf: 950178 bytes, checksum: b06d7a392d7eb491cd69e0e6e466245b (MD5) FGL_ Thesis.zip: 808566 bytes, checksum: 8722939dad64045ff8a9ffd6af43bd55 (MD5) LICENSE.txt: 4210 bytes, checksum: 0122c18517b3dd82bd6ce45e0307c717 (MD5) Previous issue date: 2019-04-22"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/104898"],"dc:language":["en"],"dc:rights":["Copyright 2019 Haroun Habeeb"],"dc:subject":["Machine Learning","Brain Decoding","Deep Learning"],"dc:title":["A spatial deep network architecture for brain decoding"],"dc:type":["text"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:42Z"}