Skip to main navigation Skip to search Skip to main content

Interpretations are Useful: Penalizing Explanations to Align Neural Networks with Prior Knowledge

  • Laura Rieger*
  • , Chandan Singh
  • , W. James Murdoch
  • , Bin Yu
  • *Corresponding author for this work
  • University of California at Berkeley

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

127 Downloads (Orbit)

Fingerprint

Dive into the research topics of 'Interpretations are Useful: Penalizing Explanations to Align Neural Networks with Prior Knowledge'. Together they form a unique fingerprint.
Sort by

Keyphrases

Social Sciences

Computer Science