5 papers
Coarse-Graining Hidden Representations: Unsupervised Neuron Selection via Mapping Entropy
Margherita Mele, Andrea Castagna, Roberto Menichetti +2
Overparameterized neural networks carry far more hidden units than a task nominally requires, raising the question of which neurons are essential and whether that distinction is le…
The bliss of dimensionality: how an unsupervised criterion identifies optimal low-resolution representations of high-dimensional datasets
Margherita Mele, Daniel Campos Moreno, Raffaello Potestio
Selecting the optimal resolution for discretizing high-dimensional data is a central problem in physics and data analysis, particularly in unsupervised settings where the underlyin…
Density of states in neural networks: an in-depth exploration of learning in parameter space
Margherita Mele, Roberto Menichetti, Alessandro Ingrosso +1
Learning in neural networks critically hinges on the intricate geometry of the loss landscape associated with a given task. Traditionally, most research has focused on finding spec…
Determining the optimal structural resolution of proteins through an information-theoretic analysis of their conformational ensemble
Margherita Mele, Raffaele Fiorentini, Thomas Tarenzi +2
The choice of structural resolution is a fundamental aspect of protein modelling, determining the balance between descriptive power and interpretability. Although atomistic simulat…
Information-theoretical measures identify accurate low-resolution representations of protein configurational space
Margherita Mele, Roberto Covino, Raffaello Potestio
A steadily growing computational power is employed to perform molecular dynamics simulations of biological macromolecules, which represents at the same time an immense opportunity…