On scientific understanding with artificial intelligence

M Krenn, R Pollice, SY Guo, M Aldeghi… - Nature Reviews …, 2022 - nature.com
An oracle that correctly predicts the outcome of every particle physics experiment, the
products of every possible chemical reaction or the function of every protein would …

Modern applications of machine learning in quantum sciences

A Dawid, J Arnold, B Requena, A Gresch… - arxiv preprint arxiv …, 2022 - arxiv.org
In these Lecture Notes, we provide a comprehensive introduction to the most recent
advances in the application of machine learning methods in quantum sciences. We cover …

Replacing neural networks by optimal analytical predictors for the detection of phase transitions

J Arnold, F Schäfer - Physical Review X, 2022 - APS
Identifying phase transitions and classifying phases of matter is central to understanding the
properties and behavior of a broad range of material systems. In recent years, machine …

Interpretable machine learning guided by physical mechanisms reveals drivers of runoff under dynamic land use changes

S Wang, Y Liu, W Wang, G Zhao, H Liang - Journal of Environmental …, 2024 - Elsevier
Human activities continuously impact water balances and cycling in watersheds, making it
essential to accurately identify the responses of runoff to dynamic changes in land use types …

Fluctuation based interpretable analysis scheme for quantum many-body snapshots

H Schlömer, A Bohrdt - SciPost Physics, 2023 - scipost.org
Microscopically understanding and classifying phases of matter is at the heart of strongly-
correlated quantum physics. With quantum simulations, genuine projective measurements …

Deep quantum graph dreaming: deciphering neural network insights into quantum experiments

T Jaouni, S Arlt, C Ruiz-Gonzalez… - Machine Learning …, 2024 - iopscience.iop.org
Despite their promise to facilitate new scientific discoveries, the opaqueness of neural
networks presents a challenge in interpreting the logic behind their findings. Here, we use a …

Characterizing out-of-distribution generalization of neural networks: application to the disordered Su–Schrieffer–Heeger model

K Cybiński, M Płodzień, M Tomza… - Machine Learning …, 2025 - iopscience.iop.org
Abstract Machine learning (ML) is a promising tool for the detection of phases of matter.
However, ML models are also known for their black-box construction, which hinders …

Learning minimal representations of stochastic processes with variational autoencoders

G Fernández-Fernández, C Manzo, M Lewenstein… - Physical Review E, 2024 - APS
Stochastic processes have found numerous applications in science, as they are broadly
used to model a variety of natural phenomena. Due to their intrinsic randomness and …

Synergistic eigenanalysis of covariance and Hessian matrices for enhanced binary classification

A Hartoyo, J Argasiński, A Trenk, K Przybylska… - arxiv preprint arxiv …, 2024 - arxiv.org
Covariance and Hessian matrices have been analyzed separately in the literature for
classification problems. However, integrating these matrices has the potential to enhance …

Speak so a physicist can understand you! TetrisCNN for detecting phase transitions and order parameters

K Cybiński, J Enouen, A Georges, A Dawid - arxiv preprint arxiv …, 2024 - arxiv.org
Recently, neural networks (NNs) have become a powerful tool for detecting quantum phases
of matter. Unfortunately, NNs are black boxes and only identify phases without elucidating …