Abstract: In recent years, deep learning (DL) applications have been widely used in both industrial and academic domains. Bugs in the DL framework have become one of the leading causes of DL model ...

Abstract: Geometric deep learning is an umbrella term for emerging techniques attempting to generalize (structured) deep neural models to non-Euclidean domains, such as graphs and manifolds. The ...

Code for predicting retinotopy from anatomy using geometric deep learning. See paper for more --> https://www.sciencedirect.com/science/article/pii/S1053811921008971 ...

Here there are some useful stuff I have written to work on topological data analysis. Some of the code was developed with specific datasets in mind, but most should generalize well.

A recently published 156-page paper from a team led by Imperial College Professor and Twitter Chief Scientist Michael Bronstein aims to geometrically unify CNN, GNN, LSTM and Transformer architectures ...