Show simple item record

dc.contributor.advisorGolland, Polina
dc.contributor.authorWang, Peiqi
dc.date.accessioned2022-06-15T13:03:30Z
dc.date.available2022-06-15T13:03:30Z
dc.date.issued2022-02
dc.date.submitted2022-03-04T20:59:47.960Z
dc.identifier.urihttps://hdl.handle.net/1721.1/143207
dc.description.abstractAdoption of machine learning models in healthcare requires end users’ trust in the system. Models that provide additional supportive evidence for their predictions promise to facilitate adoption. We define consistent evidence to be both compatible and sufficient with respect to model predictions. We propose measures of model inconsistency and regularizers that promote more consistent evidence. We demonstrate our ideas in the context of edema severity grading from chest radiographs. We demonstrate empirically that consistent models provide competitive performance while supporting interpretation.
dc.publisherMassachusetts Institute of Technology
dc.rightsIn Copyright - Educational Use Permitted
dc.rightsCopyright MIT
dc.rights.urihttp://rightsstatements.org/page/InC-EDU/1.0/
dc.titleImage Classification with Consistent Supporting Evidence
dc.typeThesis
dc.description.degreeS.M.
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
mit.thesis.degreeMaster
thesis.degree.nameMaster of Science in Electrical Engineering and Computer Science


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record