{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/110702"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/110702","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Extracting and learning structures from data","abstract":"In this work, we study models which explicitly capture and learn structures from data. For the task of supervised and unsupervised textual grounding, we propose a unified framework which links words to image concepts. A parameter between each word and image concept is learned and the learned parameters are easily interpretable. Next, for the task of generative modeling of multi-agent trajectories, we design models which share parameters based on the relationship between agents in the system to achieve permutation equivariance. This representation is particularly suitable in a multi-agent setting where the identity of the agents is unknown. We achieve better performance than conventional fully connected deep nets. Lastly, we present a framework on how to learn equivariance properties from data; this framework is based on learning how to share parameters in a model. We provide analysis on Gaussian vectors in terms on mean squared error criterion and empirically show that our approach can recover shift and permutation equivariances.","abstract_html":"In this work, we study models which explicitly capture and learn structures from data. For the task of supervised and unsupervised textual grounding, we propose a unified framework which links words to image concepts. A parameter between each word and image concept is learned and the learned parameters are easily interpretable. Next, for the task of generative modeling of multi-agent trajectories, we design models which share parameters based on the relationship between agents in the system to achieve permutation equivariance. This representation is particularly suitable in a multi-agent setting where the identity of the agents is unknown. We achieve better performance than conventional fully connected deep nets. Lastly, we present a framework on how to learn equivariance properties from data; this framework is based on learning how to share parameters in a model. We provide analysis on Gaussian vectors in terms on mean squared error criterion and empirically show that our approach can recover shift and permutation equivariances.","abstract_has_math":false,"creators":["Yeh, Raymond A"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Schwing, Alexander G","Hasegawa-Johnson, Mark","Do, Minh N","Forsyth, David"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021-09-17T02:34:38Z","date_published":"2021-09-17T02:34:38Z","updated_at":"2026-07-22T22:24:52Z","subjects":["machine learning","computer vision"],"languages":["en"],"rights":["Copyright 2021 Raymond Yeh"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/110702","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Schwing, Alexander G","Hasegawa-Johnson, Mark","Do, Minh N","Forsyth, David"]},{"key":"dc:creator","label":"Author","values":["Yeh, Raymond A"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2021-09-17T02:34:38Z","2023-09-17T02:34:57Z","2021-04-21","2021-05"]},{"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":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"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","computer vision"]}]},{"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 Raymond Yeh"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/110702"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["In this work, we study models which explicitly capture and learn structures from data. For the task of supervised and unsupervised textual grounding, we propose a unified framework which links words to image concepts. A parameter between each word and image concept is learned and the learned parameters are easily interpretable. Next, for the task of generative modeling of multi-agent trajectories, we design models which share parameters based on the relationship between agents in the system to achieve permutation equivariance. This representation is particularly suitable in a multi-agent setting where the identity of the agents is unknown. We achieve better performance than conventional fully connected deep nets. Lastly, we present a framework on how to learn equivariance properties from data; this framework is based on learning how to share parameters in a model. We provide analysis on Gaussian vectors in terms on mean squared error criterion and empirically show that our approach can recover shift and permutation equivariances.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-05-01","The student, Raymond Yeh, accepted the attached license on 2021-04-19 at 20:56.","The student, Raymond Yeh, submitted this Dissertation for approval on 2021-04-19 at 21:08.","This Dissertation was approved for publication on 2021-04-21 at 13:45.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16432 on 2021-09-16 at 17:04:03","Made available in DSpace on 2021-09-17T02:34:38Z (GMT). No. of bitstreams: 2 YEH-DISSERTATION-2021.pdf: 15431474 bytes, checksum: d271456ac1cb85a7f87549186098b914 (MD5) LICENSE.txt: 4208 bytes, checksum: 608b27144ec36d500db761844ed0482a (MD5) Previous issue date: 2021-04-21","Embargo set by: Seth Robbins for item 118545 Lift date: 2023-09-17T02:34:57Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Extracting and learning structures from data"]}]}],"canonical_facts":{"dc:contributor":["Schwing, Alexander G","Hasegawa-Johnson, Mark","Do, Minh N","Forsyth, David"],"dc:creator":["Yeh, Raymond A"],"dc:date":["2021-09-17T02:34:38Z","2023-09-17T02:34:57Z","2021-04-21","2021-05"],"dc:description":["In this work, we study models which explicitly capture and learn structures from data. For the task of supervised and unsupervised textual grounding, we propose a unified framework which links words to image concepts. A parameter between each word and image concept is learned and the learned parameters are easily interpretable. Next, for the task of generative modeling of multi-agent trajectories, we design models which share parameters based on the relationship between agents in the system to achieve permutation equivariance. This representation is particularly suitable in a multi-agent setting where the identity of the agents is unknown. We achieve better performance than conventional fully connected deep nets. Lastly, we present a framework on how to learn equivariance properties from data; this framework is based on learning how to share parameters in a model. We provide analysis on Gaussian vectors in terms on mean squared error criterion and empirically show that our approach can recover shift and permutation equivariances.","Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2023-05-01","The student, Raymond Yeh, accepted the attached license on 2021-04-19 at 20:56.","The student, Raymond Yeh, submitted this Dissertation for approval on 2021-04-19 at 21:08.","This Dissertation was approved for publication on 2021-04-21 at 13:45.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16432 on 2021-09-16 at 17:04:03","Made available in DSpace on 2021-09-17T02:34:38Z (GMT). No. of bitstreams: 2 YEH-DISSERTATION-2021.pdf: 15431474 bytes, checksum: d271456ac1cb85a7f87549186098b914 (MD5) LICENSE.txt: 4208 bytes, checksum: 608b27144ec36d500db761844ed0482a (MD5) Previous issue date: 2021-04-21","Embargo set by: Seth Robbins for item 118545 Lift date: 2023-09-17T02:34:57Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/110702"],"dc:language":["en"],"dc:rights":["Copyright 2021 Raymond Yeh"],"dc:subject":["machine learning","computer vision"],"dc:title":["Extracting and learning structures from data"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:52Z"}