Expert-Informed, User-Centric Explanations for Machine Learning
Abstract
We 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.
Cite
Text
Pazzani et al. "Expert-Informed, User-Centric Explanations for Machine Learning." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I11.21491Markdown
[Pazzani et al. "Expert-Informed, User-Centric Explanations for Machine Learning." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/pazzani2022aaai-expert/) doi:10.1609/AAAI.V36I11.21491BibTeX
@inproceedings{pazzani2022aaai-expert,
title = {{Expert-Informed, User-Centric Explanations for Machine Learning}},
author = {Pazzani, Michael J. and Soltani, Severine and Kaufman, Robert and Qian, Samson and Hsiao, Albert},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2022},
pages = {12280-12286},
doi = {10.1609/AAAI.V36I11.21491},
url = {https://mlanthology.org/aaai/2022/pazzani2022aaai-expert/}
}