Toward harnessing user feedback for machine learning Public Deposited

http://ir.library.oregonstate.edu/concern/technical_reports/m039k6035

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • There has been little research into how end users might be able to communicate advice to machine learning systems. If this resource--the users themselves--could somehow work hand-in-hand with machine learning systems, the accuracy of learning systems could be improved and the users' understanding and trust of the system could improve as well. We conducted a think-aloud study to see how willing users were to provide feedback and to understand what kinds of feedback users could give. Users were shown explanations of machine learning predictions and asked to provide feedback to improve the predictions. We found that users had no difficulty providing generous amounts of feedback. The kinds of feedback ranged from suggestions for reweighting of features to proposals for new features, feature combinations, relational features, and wholesale changes to the learning algorithm. The results show that user feedback has the potential to significantly improve machine learning systems, but that learning algorithms need to be extended in several ways to be able to assimilate this feedback.
Resource Type
Date Available
Date Issued
Series
Keyword
Subject
Rights Statement
Publisher
Peer Reviewed
Language
Replaces
Additional Information
  • description.provenance : Made available in DSpace on 2012-05-24T15:56:52Z (GMT). No. of bitstreams: 1 Toward harnessing user feedback for machine learning.pdf: 140779 bytes, checksum: 021feaf6a3e246d34d3c7ccf1c9c03aa (MD5) Previous issue date: 2006-10-02
  • description.provenance : Approved for entry into archive by Laura Wilson(laura.wilson@oregonstate.edu) on 2012-05-24T15:56:52Z (GMT) No. of bitstreams: 1 Toward harnessing user feedback for machine learning.pdf: 140779 bytes, checksum: 021feaf6a3e246d34d3c7ccf1c9c03aa (MD5)
  • description.provenance : Submitted by Laura Wilson (laura.wilson@oregonstate.edu) on 2012-05-24T15:55:58Z No. of bitstreams: 1 Toward harnessing user feedback for machine learning.pdf: 140779 bytes, checksum: 021feaf6a3e246d34d3c7ccf1c9c03aa (MD5)

Relationships

In Administrative Set:
Last modified: 07/18/2017

Downloadable Content

Download PDF
Citations:

EndNote | Zotero | Mendeley

Items