ADR Awareness Centre

We present non-Markov decision processes, where rewards and dynamics can depend on the history of events. This is contrast with Markov Decision Processes, where the dependency is limited to the last state and action.

A package for implementing and simulating decentralized Graph Neural Network algorithms for classification of peer-to-peer nodes.

We propose an architecture-agnostic approach that jointly discovers factors representing spatial parts and their appearances in an entirely unsupervised fashion.

Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods.

Inspired by scenario writing methods to foster discussion on the societal implications of technology and regulation, the paper develops a ‘legal fiction scenario’ to anticipate the impact of the proposed European 

The project aimed to implement fair automatic recognition by offering guidance in policy development on an European and national level.