22557e7132
- 7-8월 초기 구축 문서 12개를 _archive/troubleshooting/2025_07-08_initial_setup/로 이동 - book/300_architecture/390_human_in_the_loop_intent_learning.md를 journey/research/intent_classification/로 이동 (개발 여정 문서) - 빈 폴더 제거 (journey/assets/*)
666 B
666 B
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
- Authors: Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viegas, Rory Sayres
- Year: 2018
- Summary: TCAV moves beyond explaining predictions in terms of low-level features and instead explains them in terms of high-level, human-understandable concepts. It quantifies the degree to which a user-defined concept (e.g., 'stripes' for a zebra classifier) is important to a model's prediction for a class of inputs. This allows for more global and intuitive explanations.
- Link: https://arxiv.org/abs/1711.11279