ADR Awareness Centre

In this study we propose a novel approach to audio phylogeny, i.e. the detection of relationships and transformations within a set of near-duplicate audio items, by leveraging a deep neural network for efficiency and extensibility.

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

Graph Neural Networks (GNNs) have seen a dramatic increase in popularity thanks to their ability to understand relations between graph nodes.

Code for Word-Class Embeddings (WCEs), a form of supervised embeddings especially suited for multiclass text classification.

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

Exemplar-free class-incremental learning is very challenging due to the negative effect of catastrophic forgetting.