Research theme 03

Simple machine learning

Statistical-physics inspired models for interpretable learning, optimization and representations.

Overview

This newer line of work uses simple models [bai25] to study aspects of machine learning (ML) that can be difficult to isolate in large architectures. The emphasis is on mechanisms rather than scale.

Questions include how stochastic dynamics, optimization rules, noise and representation spaces shape learning. Minimal models make it possible to compare intuition from statistical physics with behaviour observed in learning algorithms.

This theme is meant to remain flexible: it can include generative models, latent-variable approaches, learning dynamics and applications where simplified models expose the relevant structure.

Restricted Boltzmann machines are examples of simple, interpretable ML models. Their application to amino acid sequences in protein helices and sheets reveals what was termed the effective hydrophobicity of amino acids, which determines how Nature uses them in the hydrophobic patterns of proteins [bra23].

In addition, thanks also to the growing expertise of students in the master's program in Physics of Data at the University of Padova, the application of more complex ML models led to practical advances, for example in medical sciences [bra22,zan25] and the preservation of artistic paintings [cal25].

Selected papers

[bai25] Emergence of Nonequilibrium Latent Cycles in Unsupervised Generative Modeling

M Baiesi, A Rosso,
arXiv preprint arXiv:2512.11415

A simple generative model showing better performance when operating far from equilibrium, where it visits latent representations in cycles.

Link

[bra23] Interpretable machine learning of amino acid patterns in proteins: a statistical ensemble approach

A Braghetto, E Orlandini, M Baiesi,
Journal of Chemical Theory and Computation 19, 6011 (2023)

Restricted Boltzmann machines applied to study sequences of amino acids in proteins.

Link

[bra22] Radiomics and deep learning methods for the prediction of 2-year overall survival in LUNG1 dataset

A Braghetto, F Marturano, M Paiusco, M Baiesi, A Bettinelli,
Scientific Reports 12, 14132 (2022)

Study of a database of tumor images with various ML tools.

Link

[zan25] xEEGNet: towards explainable AI in EEG dementia classification

A Zanola, L Fabrice Tshimanga, F Del Pup, M Baiesi, M Atzori,
Journal of Neural Engineering 22, 046042 (2025)

This work introduces a compact and explainable neural network for electroencephalography (EEG) data analysis, which reduces overfitting through a major parameter reduction.

Link

[cal25] Machine learning and numerical simulations for predicting critical crack conditions in wooden panels

A Califano, P Foti, M Baiesi, R Sepe, F Berto, C Bertolin,
International Journal of Structural Integrity 16, 914 (2025)

A study of cracks in wooden panels that also uses tools from machine learning.

Link