Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 30, 2017Open Access

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

View Full Paper
Ask AI
Bookmark
Share

Authors

BKBeen KimGoogle (United States)MWMartin WattenbergUniversity of Tennessee at MartinJGJustin GilmerWorthing Hospital

Discussion

Loading...

Member takes

Implication

Key Points

Key points are not available for this paper at this time.

Cite This Study

Kim et al. (2017) studied this question.

synapsesocial.com/papers/6a0ebb63a14f152feaf9c41fhttps://doi.org/10.48550/arxiv.1711.11279
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Graph-Sparse LDA: A Topic Model with Structured Sparsity2015 · 48 citations
  2. 2ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases2017 · 16 citations
  3. 3Adversarial Machine Learning at Scale2016 · 368 citations