Explainable and Safe AI Research Landscape Map
Surveys
Ex. Techniques
A. Adadi and M. Berrada, “Peeking inside the black-box"
R. Ashmore, R. Calinescu, and C. Paterson, “Assuring the machine learning lifecycle
O. Biran and C. Cotton, “Explanation and justification in machine
learning
Mohseni et al "Explainable Artificial Intelligence: A Survey."
F. K. Dosilovi, M. Brci, and N. Hlupi, “Explainable artificial intelli-gence: A survey,”
Theory
T. Miller, “Explanation in artificial intelligence: Insights from the social
sciences,”
S. Mohseni, N. Zarei, and E. D. Ragan, “A survey of evaluation methods
and measures for interpretable machine learning
Interpretability methods
Explanations
Local
M. T. Ribeiro, S. Singh, and C. Guestrin,“why should i trust you? explaining the predictions of any classifier, ” https://arxiv.org/abs/1602.04938, 2016.
Saliency maps
T. Zahavy, N. B. Zrihem, and S. Mannor, “Graying the black box:Understanding dqns,”https://arxiv.org/abs/1602.02658, 2016.
Global
Transparancy
Evaluation of Explanation
Safety Critical Systems
Safety Cases
Assurance
Machine Learning
ML Methods
RL
Neural Nets
T. Zahavy, N. B. Zrihem, and S. Mannor, “Graying the black box:Understanding dqns
C. Olah, L. Schubert, and A. Mordvintsev, “Feature visualization how neural networks build up their understanding of images
Supervised Learning
Unsupervised Learning
Classifiers
M. T. Ribeiro, S. Singh, and C. Guestrin,“why should i trust you? explaining the predictions of any classifier, ” https://arxiv.org/abs/1602.04938, 2016.
C. Otte, “Safe and interpretable machine learning a methodologicalreview,”
L. A. Hendricks, Z. Akata, M. Rohrbach, J. Donahue, B. Schiele,and T. D. and, “Generating visual explanations,”
Applications
Health Care
Autonomous Vehicles
Requirements and needs
Legality
GDPR (Goodman & Flaxman)
R. Budishet al., “Accountability of ai under the law: The role of ex-planation,”
User Needs
Safety
Technical
Theory of Explanations
Philosophy
Definitions
Transparency vs Explanations
Z. C. Lipton, “The mythos of model interpretability,”