Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations
-
- Andrew Slavin Ross
- Harvard University
-
- Michael C. Hughes
- Harvard University
-
- Finale Doshi-Velez
- Harvard University
書誌事項
- 公開日
- 2017-08
- DOI
-
- 10.24963/ijcai.2017/371
- 公開者
- International Joint Conferences on Artificial Intelligence Organization
説明
<jats:p>Expressive classifiers such as neural networks are among the most accurate supervised learning methods in use today, but their opaque decision boundaries make them difficult to trust in critical applications. We propose a method to explain the predictions of any differentiable model via the gradient of the class label with respect to the input (which provides a normal to the decision boundary). Not only is this approach orders of magnitude faster at identifying input dimensions of high sensitivity than sample-based perturbation methods (e.g. LIME), but it also lends itself to efficiently discovering multiple qualitatively different decision boundaries as well as decision boundaries that are consistent with expert annotation. On multiple datasets, we show our approach generalizes much better when test conditions differ from those in training.</jats:p>
収録刊行物
-
- Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
-
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence 2662-2670, 2017-08
International Joint Conferences on Artificial Intelligence Organization
