DeepNNK: Explaining deep models and their generalization using polytope interpolation
arXiv:2007.10505
Abstract
Modern machine learning systems based on neural networks have shown great success in learning complex data patterns while being able to make good predictions on unseen data points. However, the limited interpretability of these systems hinders further progress and application to several domains in the real world. This predicament is exemplified by time consuming model selection and the difficulties faced in predictive explainability, especially in the presence of adversarial examples. In this paper, we take a step towards better understanding of neural networks by introducing a local polytope interpolation method. The proposed Deep Non Negative Kernel regression (NNK) interpolation framework is non parametric, theoretically simple and geometrically intuitive. We demonstrate instance based explainability for deep learning models and develop a method to identify models with good generalization properties using leave one out estimation. Finally, we draw a rationalization to adversarial and generative examples which are inevitable from an interpolation view of machine learning.
arXiv commentSubmitted for review at ICPR 2020
References in corpus (10)
- Towards A Rigorous Science of Interpretable Machine Learning
- Wide Residual Networks
- Understanding deep learning requires rethinking generalization
- Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
- Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
- Risk bounds for statistical learning
- Overfitting or perfect fitting? Risk bounds for classification and regression rules that interpolate
- Do CIFAR-10 Classifiers Generalize to CIFAR-10?
- Does data interpolation contradict statistical optimality?
- The Ladder: A Reliable Leaderboard for Machine Learning Competitions