Search Results for author: Ainkaran Santhirasekaram

Found 2 papers, 2 papers with code

Hierarchical Symbolic Reasoning in Hyperbolic Space for Deep Discriminative Models

1 code implementation • 5 Jul 2022 • Ainkaran Santhirasekaram, Avinash Kori, Andrea Rockall, Mathias Winkler, Francesca Toni, Ben Glocker

We achieve this by using the natural properties of \emph{hyperbolic geometry} to more efficiently model a hierarchy of symbolic features and generate \emph{hierarchical symbolic rules} as part of our explanations.

Feature Importance

Paper
Code

Vector Quantisation for Robust Segmentation

1 code implementation • 5 Jul 2022 • Ainkaran Santhirasekaram, Avinash Kori, Mathias Winkler, Andrea Rockall, Ben Glocker

The reliability of segmentation models in the medical domain depends on the model's robustness to perturbations in the input space.

Data Augmentation Dictionary Learning +1

Paper
Code

Cannot find the paper you are looking for? You can Submit a new open access paper.