Path-Based Visual Explanation
Publication
, Chapter
Pourvali, M; Jin, Y; Sheng, C; Meng, Y; Wang, L; Gorkovenko, M; Hu, C
January 1, 2020
The ability to explain the behavior of a Machine Learning (ML) model as a black box to people is becoming essential due to wide usage of ML applications in critical areas ranging from medicine to commerce. Case-Based Reasoning (CBR) received a special interest among other methods of providing explanations for model decisions due to the fact that it can easily be paired with a black box and then can propose a post-hoc explanation framework. In this paper, we propose a CBR-Based method to not only explain a model decision but also provide recommendations to the user in an easily understandable visual interface. Our evaluation of the method in a user study shows interesting results.
Duke Scholars
DOI
Publication Date
January 1, 2020
Volume
12431 LNAI
Start / End Page
454 / 466
Related Subject Headings
- Artificial Intelligence & Image Processing
- 46 Information and computing sciences
Citation
APA
Chicago
ICMJE
MLA
NLM
Pourvali, M., Jin, Y., Sheng, C., Meng, Y., Wang, L., Gorkovenko, M., & Hu, C. (2020). Path-Based Visual Explanation (Vol. 12431 LNAI, pp. 454–466). https://doi.org/10.1007/978-3-030-60457-8_37
Pourvali, M., Y. Jin, C. Sheng, Y. Meng, L. Wang, M. Gorkovenko, and C. Hu. “Path-Based Visual Explanation,” 12431 LNAI:454–66, 2020. https://doi.org/10.1007/978-3-030-60457-8_37.
Pourvali M, Jin Y, Sheng C, Meng Y, Wang L, Gorkovenko M, et al. Path-Based Visual Explanation. In 2020. p. 454–66.
Pourvali, M., et al. Path-Based Visual Explanation. Vol. 12431 LNAI, 2020, pp. 454–66. Scopus, doi:10.1007/978-3-030-60457-8_37.
Pourvali M, Jin Y, Sheng C, Meng Y, Wang L, Gorkovenko M, Hu C. Path-Based Visual Explanation. 2020. p. 454–466.
DOI
Publication Date
January 1, 2020
Volume
12431 LNAI
Start / End Page
454 / 466
Related Subject Headings
- Artificial Intelligence & Image Processing
- 46 Information and computing sciences