1 code implementation • 15 May 2024 • Emanuele Loffredo, Mauro Pastore, Simona Cocco, Rémi Monasson
Class imbalance in real-world data poses a common bottleneck for machine learning tasks, since achieving good generalization on under-represented examples is often challenging.
no code implementations • 6 Apr 2023 • Eugenio Mauri, Simona Cocco, Rémi Monasson
We study transition paths in energy landscapes over multi-categorical Potts configurations using the mean-field approach introduced by Mauri et al., {\em Phys Rev Lett 130, 158402 (2023)}.
no code implementations • 23 Jun 2022 • Jorge Fernandez-de-Cossio-Diaz, Simona Cocco, Remi Monasson
A goal of unsupervised machine learning is to build representations of complex high-dimensional data, with simple relations to their properties.
no code implementations • 22 Apr 2022 • Eugenio Mauri, Simona Cocco, Rémi Monasson
Identifying and characterizing mutational paths is an important issue in evolutionary biology and in bioengineering.
1 code implementation • 13 Jul 2021 • Clément Roussel, Simona Cocco, Rémi Monasson
Restricted Boltzmann Machines (RBM) are bi-layer neural networks used for the unsupervised learning of model distributions from data.
no code implementations • 22 Oct 2020 • Marco Molari, Rémi Monasson, Simona Cocco
We then extend our results to the full population, both in the absence and presence of competition for T-cell help, and quantify the population survival probability as a function of Ag concentration and initial population size.
no code implementations • 30 Jun 2020 • Hong-Li Zeng, Eugenio Mauri, Vito Dichio, Simona Cocco, Remi Monasson, Erik Aurell
We consider a population evolving due to mutation, selection and recombination, where selection includes single-locus terms (additive fitness) and two-loci terms (pairwise epistatic fitness).
no code implementations • 30 Dec 2019 • Moshir Harsh, Jérôme Tubiana, Simona Cocco, Remi Monasson
Distributions of data or sensory stimuli often enjoy underlying invariances.
no code implementations • 18 Feb 2019 • Jérôme Tubiana, Simona Cocco, Rémi Monasson
A Restricted Boltzmann Machine (RBM) is an unsupervised machine-learning bipartite graphical model that jointly learns a probability distribution over data and extracts their relevant statistical features.
1 code implementation • 23 Mar 2018 • Jérôme Tubiana, Simona Cocco, Rémi Monasson
Statistical analysis of evolutionary-related protein sequences provides insights about their structure, function, and history.
1 code implementation • 3 Mar 2017 • Simona Cocco, Christoph Feinauer, Matteo Figliuzzi, Remi Monasson, Martin Weigt
In the course of evolution, proteins undergo important changes in their amino acid sequences, while their three-dimensional folded structure and their biological function remain remarkably conserved.