TED
Michael Hind, Dennis Wei, Murray S. Campbell et al. · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · 2019
Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions. However, as many of these systems are opaque in their operation, there is a growing demand for such systems to provide explanations for their decisions. Conventional approaches to this problem attempt to expose or discover the inner workings of a machine learning model with the hope that the resulting explanations will be meaningful to the consumer. In contrast, this paper suggests a new approach to this problem. It introduces a simple, practical framework, called Teaching Explanations for Decisions (TED), that provides meaningful explanations that match the mental model of the consumer. We illustrate the generality and effectiveness of this approach with two different examples, resulting in highly accurate explanations with no loss of prediction accuracy for these two examples.
Cited by 92 works. doi:10.1145/3306618.3314273
Authors
- Michael Hind
- Dennis Wei
- Murray S. Campbell
- Noel Codella
- Amit Dhurandhar
- Aleksandra Mojsilović
- Karthikeyan Natesan Ramamurthy
- Kush R. Varshney
References
- "Why Should I Trust You?"
- Deep Learning
- A Unified Approach to Interpreting Model Predictions
- The Mythos of Model Interpretability
- Towards A Rigorous Science of Interpretable Machine Learning
- Intelligible Models for HealthCare
- Methods for interpreting and understanding deep neural networks
- Why a Right to Explanation of Automated Decision-Making Does Not Exist in the General Data Protection Regulation
- Rationalizing Neural Predictions
- Discovering localized attributes for fine-grained recognition