1

Mesh convolutional neural networks for wall shear stress estimation in 3D artery models

We propose Mesh Convolution Neural Networks for rapid estimation of CFD parameters on arteries such as wall shear stress (WSS)

Efficient Neural Causal Discovery without Acyclicity Constraints

We present ENCO, an efficient structure learning method that leverages observational and interventional data and scales to graphs with a thousand variables. Published at CausalUAI 2021.

Categorical Normalizing Flows via Continuous Transformations

We explore the application of normalizing flows on categorical data, and propose GraphCNF a permutation-invariant generative model on graphs. Published at ICLR 2021.

Deep Reasoning - Hardware Accelerated Artificial Intelligence

We investigate deep-learning based heuristics for first-order automated theorem provers.