Interpretability Of Classification Models
Interpretability of Classification Models is the extent to which the internal mechanisms and decision logic of a classification model in land cover mapping can be understood and explained by human analysts, distinguishing it from purely predictive performance by emphasizing transparency, traceability, and comprehensibility of model behavior.
234
Publications
14.4K
Citations
867
Authors
409
Institutions
Publications per year
2017–2026
128
Parents
234
Comprehensible classification models
Alex A. Freitas · ACM SIGKDD Explorations Newsletter · 2014 · 570 citations
Interpretability of deep learning models: A survey of results
Supriyo Chakraborty, Richard Tomsett, Ramya Raghavendra et al. · 2017 · 431 citations
A Benchmark for Interpretability Methods in Deep Neural Networks
Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans et al. · arXiv (Cornell University) · 2018 · 382 citations · Full text
1–5 of 234
867
3
h-index
2
h-index
2
h-index
Institute of Psychology, Chinese Academy of Sciences, China
2 publications · 65 citations
2
h-index
2
h-index
1–5 of 867
409
Stanford University
Stanford, United States
4 h-index
9 publications
1.9K citations
University of Antwerp
Antwerp, Belgium
4 h-index
7 publications
302 citations

The University of Sydney
Sydney, Australia
4 h-index
5 publications
248 citations
University of California, Berkeley
Berkeley, United States
4 h-index
8 publications
10.5K citations
University of Tartu
Tartu, Estonia
4 h-index
11 publications
824 citations
University of Kent
Canterbury, United Kingdom
4 h-index
6 publications
723 citations
Massachusetts Institute of Technology
Cambridge, United States
4 h-index
9 publications
576 citations

Cornell University
Ithaca, United States
3 h-index
4 publications
174 citations
1–8 of 409
Repository · 9 publications · 557 citations
9
h-index
5 publications · 96 citations
5
h-index
3 publications · 128 citations
3
h-index
3 publications · 228 citations
3
h-index
3 publications · 149 citations
3
h-index
1–5