3 papers
cond-mat.dis-nn2025
On the role of non-linear latent features in bipartite generative neural networks
Tony Bonnaire, Giovanni Catania, Aurélien Decelle +1
We investigate the phase diagram and memory retrieval capabilities of bipartite energy-based neural networks, namely Restricted Boltzmann Machines (RBMs), as a function of the prio…
astro-ph.CO2021
Shape and connectivity of groups and clusters: Impact of dynamical state and accretion history
C. Gouin, T. Bonnaire, N Aghanim
Matter distribution around clusters is highly anisotropic from their being the nodes of the cosmic web. Clusters' shape and the number of filaments they are connected to, i.e., the…
stat.ML2020
Cascade of Phase Transitions for Multi-Scale Clustering
T. Bonnaire, A. Decelle, N. Aghanim
We present a novel framework exploiting the cascade of phase transitions occurring during a simulated annealing of the Expectation-Maximisation algorithm to cluster datasets with m…