Personalizing machine learning systems with explanatory debugging Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/2514np58w

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • How can end users efficiently influence the predictions that machine learning systems make on their behalf? Traditional systems rely on users to provide examples of how they want the learning system to behave, but this is not always practical for the user, nor efficient for the learning system. This dissertation explores a different personalization approach: a two-way cycle of explanations, in which the learning system explains the reasons for its predictions to the end user, who can then explain any necessary corrections back to the system. In formative work, we study the feasibility of explaining a machine learning system's reasoning to end users and whether this might help users explain corrections back to the learning system. We then conduct a detailed study of how learning systems should explain their reasoning to end users. We use the results of this formative work to inform Explanatory Debugging, our explanation-centric approach for personalizing machine learning systems, and present an example of how this novel approach can be instantiated in a text classification system. Finally, we evaluate the effectiveness of Explanatory Debugging versus a traditional learning system, finding that explanations of the learning system's reasoning improved study participants' understanding by over 50% (compared with participants who used the traditional system) and participants' corrections to this reasoning were up to twice as efficient as providing examples to the learning system.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Keyword
Subject
Rights Statement
Peer Reviewed
Language
Replaces
Additional Information
  • description.provenance : Submitted by Todd Kulesza (kuleszat@onid.orst.edu) on 2014-12-10T00:33:26Z No. of bitstreams: 2 KuleszaToddD2014.pdf: 8918539 bytes, checksum: 9b259d995aa5aafcc741eaaa8a499e67 (MD5) license_rdf: 1527 bytes, checksum: d4743a92da3ca4b8c256fdf0d7f7680f (MD5)
  • description.provenance : Approved for entry into archive by Laura Wilson(laura.wilson@oregonstate.edu) on 2014-12-10T19:13:02Z (GMT) No. of bitstreams: 2 KuleszaToddD2014.pdf: 8918539 bytes, checksum: 9b259d995aa5aafcc741eaaa8a499e67 (MD5) license_rdf: 1527 bytes, checksum: d4743a92da3ca4b8c256fdf0d7f7680f (MD5)
  • description.provenance : Rejected by Julie Kurtz(julie.kurtz@oregonstate.edu), reason: Rejecting because the pages are not numbered to the end, they stop on page 112, Appendix A. Add pages numbers consecutively starting on page 113 to the end. Everything else looks good. Once revised log back into ScholarsArchive and go to the upload page. Replace the attached file with the revised file and resubmit. Thanks, Julie on 2014-12-09T21:33:36Z (GMT)
  • description.provenance : Made available in DSpace on 2014-12-10T19:13:02Z (GMT). No. of bitstreams: 2 KuleszaToddD2014.pdf: 8918539 bytes, checksum: 9b259d995aa5aafcc741eaaa8a499e67 (MD5) license_rdf: 1527 bytes, checksum: d4743a92da3ca4b8c256fdf0d7f7680f (MD5) Previous issue date: 2014-12-01
  • description.provenance : Approved for entry into archive by Julie Kurtz(julie.kurtz@oregonstate.edu) on 2014-12-10T17:49:28Z (GMT) No. of bitstreams: 2 KuleszaToddD2014.pdf: 8918539 bytes, checksum: 9b259d995aa5aafcc741eaaa8a499e67 (MD5) license_rdf: 1527 bytes, checksum: d4743a92da3ca4b8c256fdf0d7f7680f (MD5)
  • description.provenance : Submitted by Todd Kulesza (kuleszat@onid.orst.edu) on 2014-12-09T00:05:30Z No. of bitstreams: 2 license_rdf: 1527 bytes, checksum: d4743a92da3ca4b8c256fdf0d7f7680f (MD5) KuleszaToddD2014.pdf: 5919145 bytes, checksum: ff4b55a4b255b69a3ed5f6a90cdca92a (MD5)

Relationships

Parents:

This work has no parents.

Last modified

Downloadable Content

Download PDF

Items