Expert-Informed, User-Centric Explanations for Machine Learning
Keywords:Machine Learning, Explainable AI, Cognitive Science, Ethnography
AbstractWe argue that the dominant approach to explainable AI for explaining image classification, annotating images with heatmaps, provides little value for users unfamiliar with deep learning. We argue that explainable AI for images should produce output like experts produce when communicating with one another, with apprentices, and with novices. We provide an expanded set of goals of explainable AI systems and propose a Turing Test for explainable AI.
How to Cite
Pazzani, M., Soltani, S., Kaufman, R., Qian, S., & Hsiao, A. (2022). Expert-Informed, User-Centric Explanations for Machine Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 12280-12286. https://doi.org/10.1609/aaai.v36i11.21491
Senior Member Presentation: Blue Sky Papers