Find below EMERGE’s news articles, press releases, digests of scientific publications, as well as other outreach materials.
Publication: Consensus in the Weighted Voter Model with Noise-Free and Noisy Observations
06 May 2025
In this work, EMERGE partners from the University of Bristol present an exact finite-population analysis of the best-of-two model on complete as well as regular network topologies.
Publication: A Model of Memristive Nanowire Neuron for Recurrent Neural Networks
25 April 2025
In this work, EMERGE partners from the University of Pisa introduce a novel discrete-time model for a neural processing unit based on the physical principles of memristive nanowires.
Publication: Towards Adaptive and Stable Compositional Assemblies of Recurrent Neural Network Modules
25 April 2025
EMERGE partners from the University of Pisa propose two strategies to allow adaptivity of the internal weights of RNN modules while ensuring contractive dynamics from each.
Publication: Replay-free Online Continual Learning with Self-Supervised MultiPatches
25 April 2025
In this work, EMERGE partners from the University of Pisa propose Continual MultiPatches (CMP), an effective plug-in for existing OCL self-supervised learning strategies that avoids the use of replay samples.
Publication: Human cooperation with artificial agents varies across countries.
22 April 2025
In this work, EMERGE partners from the Ludwig Maximilian University of Munich examined people’s willingness to cooperate with artificial agents and humans in two classic economic games requiring a choice between self-interest and mutual benefit.
Publication: Cellular Au-Tonnetz: A Unified Audio-Visual MIDI Generator Using Tonnetz, Cellular Automata, and IoT
20 April 2025
In this work, EMERGE partners from the University of Bristol present a detailed description of an innovative tool for music creation that merges sound and light through a unified system.
Publication: On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems
11 April 2025
In this work, EMERGE partners from the University of Pisa present SWAN, a uniquely parameterized GNN model with antisymmetry both in space and weight domains, in order to obtain non-dissipativity.
Sabine Hauert at The Royal Institution.
26 March 2025
EMERGE partner was a recent lecturer at RI, where she explained how recent developments in robotics and AI can revolutionise our lives, and why swarm systems can be trusted.
Publication: A memristive computational neural network model for time-series processing
20 March 2025
In this work, EMERGE partners from the University of Pisa introduce a novel computational framework inspired by the physics of memristive devices and systems, which are embed into the context of Recurrent Neural Networks (RNNs) for time-series processing.
