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 …

[PDF][PDF] tightbinder: A Python package for semi-empirical tight-binding models of crystalline and disordered solids

AJ Uría-Álvarez, JJ Palacios - Journal of Open Source Software, 2024 - joss.theoj.org
Summary tightbinder is a Python package for Slater-Koster, semi-empirical tight-binding
calculations of the electronic structure of solids. Tight-binding models are ubiquitous in …

[PDF][PDF] Design of plasmonic superconducting transition-edge-sensors with neural networks

SG Rodrigo, C Pobes, L Martín-Moreno, AC Lasheras - 2022 - um.es
We demonstrate the use of neural networks (NN) to improve the design of plasmonic
nanostructures. The scattering properties of a plasmonic nanostructure calculated by a slow …