Abstract

The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state. In addition, many systems, such as image classifiers, operate on low-level features rather than high-level concepts. To address these challenges, we introduce Concept Activation Vectors (CAVs), which provide an interpretation of a neural net's internal state in terms of human-friendly concepts. The key idea is to view the high-dimensional internal state of a neural net as an aid, not an obstacle. We show how to use CAVs as part of a technique, Testing with CAVs (TCAV), that uses directional derivatives to quantify the degree to which a user-defined concept is important to a classification result--for example, how sensitive a prediction of "zebra" is to the presence of stripes. Using the domain of image classification as a testing ground, we describe how CAVs may be used to explore hypotheses and generate insights for a standard image classification network as well as a medical application.

Keywords

InterpretabilityComputer scienceArtificial intelligenceInterpretation (philosophy)Image (mathematics)Domain (mathematical analysis)Machine learningFeature (linguistics)Artificial neural networkKey (lock)Contextual image classificationPattern recognition (psychology)Mathematics

Affiliated Institutions

Related Publications

Publication Info

Year
2017
Type
preprint
Citations
476
Access
Closed

External Links

View on DOI.org

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

476
OpenAlex

Cite This

Been Kim, Martin Wattenberg, Justin Gilmer et al. (2017). Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV). arXiv (Cornell University) . https://doi.org/10.48550/arxiv.1711.11279

Identifiers

DOI
10.48550/arxiv.1711.11279