Hold me tight! Influence of discriminative features on deep network boundaries
NIPS 2020, 2020.
Important insights towards the explainability of neural networks and their properties reside in the formation of their decision boundaries. In this work, we borrow tools from the field of adversarial robustness and propose a new framework that permits to relate the features of the dataset with the distance of data samples to the decisio...More
PPT (Upload PPT)