Wexler, James

2 publications

NeurIPS 2019 Towards Automatic Concept-Based Explanations Amirata Ghorbani, James Wexler, James Y Zou, Been Kim

ICML 2018 Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viegas, Rory Sayres