Unmasking Clever Hans predictors and assessing what machines really learn.

Volume: 10, Issue: 1, Pages: 1096 - 1096
Published: Mar 11, 2019
Abstract
Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly intelligent behavior. Here we apply recent techniques for explaining decisions of state-of-the-art learning machines and analyze various tasks from computer vision and arcade games. This showcases a spectrum of problem-solving behaviors ranging from naive and short-sighted, to well-informed and strategic. We observe that...
Paper Details
Title
Unmasking Clever Hans predictors and assessing what machines really learn.
Published Date
Mar 11, 2019
Volume
10
Issue
1
Pages
1096 - 1096
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.