Ivars Namatēvs, Kaspars Sudars, Artis Dobrājs. Interpretability versus Explainability: Classification for Understanding Deep Learning Systems and Models. Computer Assisted Methods in Engineering and Science, 29(4), 297 - 356 pp. IPPT PAN, 2022.
Bibtex citation:
Bibtex citation:
@article{13094_2022,
author = {Ivars Namatēvs and Kaspars Sudars and Artis Dobrājs},
title = {Interpretability versus Explainability: Classification for Understanding Deep Learning Systems and Models},
journal = {Computer Assisted Methods in Engineering and Science},
volume = {29},
issue = {4},
pages = {297 - 356},
publisher = {IPPT PAN},
year = {2022}
}
author = {Ivars Namatēvs and Kaspars Sudars and Artis Dobrājs},
title = {Interpretability versus Explainability: Classification for Understanding Deep Learning Systems and Models},
journal = {Computer Assisted Methods in Engineering and Science},
volume = {29},
issue = {4},
pages = {297 - 356},
publisher = {IPPT PAN},
year = {2022}
}
Abstract: The techniques of explainability and interpretability are not alternatives for many real-world problems, as recent studies often suggest. Interpretable machine learning is not a subset of explainable artificial intelligence or vice versa. While the former aims to build glass-box predictive models, the latter seeks to understand a black box using an explanatory model, a surrogate model, an attribution approach, relevance importance, or other statistics. There is concern that definitions, approaches, and methods do not match, leading to the inconsistent classification of deep learning systems and models for interpretation and explanation. In this paper, we attempt to systematically evaluate and classify the various basic methods of interpretability and explainability used in the field of deep learning. One goal of this paper is to provide specific definitions for interpretability and explainability in Deep Learning. Another goal is to spell out the various research methods for interpretability and explainability through the lens of the literature to create a systematic classifier for interpretability and explainability in deep learning. We present a classifierthat summarizes the basic techniques and methods of explainability and interpretability models. The evaluation of the classifier provides insights into the challenges of developing a complete and unified deep learning framework for interpretability and explainability concepts, approaches, and techniques.
Quartile: Q2