DeepNNK: Explaining deep models and their generalization using polytope interpolation
This addresses the problem of interpretability and generalization in deep learning for researchers and practitioners, though it is incremental as it builds on existing interpolation concepts.
The paper tackles the limited interpretability of neural networks by introducing Deep Non Negative Kernel regression (NNK), a local polytope interpolation method, to provide instance-based explainability and identify models with good generalization properties using leave-one-out estimation.
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.