Luca M. Ghiringhelli

Jan 15, 2025 | pubs.rsc.org | Daniel Speckhard |Humboldt-Universität zu Berlin |Luca M. Ghiringhelli |Tim Bechtel

Big data has ushered in a new wave of predictive power using machine-learning models. In this work, we assess what big means in the context of typical materials-science machine-learning problems. This concerns not only data volume, but also data quality and veracity as much as infrastructure issues.

Oct 12, 2023 | arxiv.org | Luca M. Ghiringhelli

[Submitted on 12 Oct 2023 (v1), last revised 1 Mar 2024 (this version, v3)] Title:Emergence of Latent Binary Encoding in Deep Neural Network Classifiers Download a PDF of the paper titled Emergence of Latent Binary Encoding in Deep Neural Network Classifiers, by Luigi Sbail\`o and Luca Ghiringhelli Download PDF HTML (experimental) Abstract:We investigate the emergence of binary encoding within the latent space of deep-neural-network classifiers.

Sep 14, 2023 | nature.com | Luca M. Ghiringhelli |Carsten Baldauf |Tristan Bereau |Christian Carbogno |Stefano Curtarolo |Claudia Draxl | +9 more

The expansive production of data in materials science, their widespread sharing and repurposing requires educated support and stewardship. In order to ensure that this need helps rather than hinders scientific work, the implementation of the FAIR-data principles (Findable, Accessible, Interoperable, and Reusable) must not be too narrow.

Jun 24, 2023 | nature.com | Matthias Scheffler |Luca M. Ghiringhelli

AbstractReliable artificial-intelligence models have the potential to accelerate the discovery of materials with optimal properties for various applications, including superconductivity, catalysis, and thermoelectricity. Advancements in this field are often hindered by the scarcity and quality of available data and the significant effort required to acquire new data.

May 18, 2023 | arxiv.org | Luca M. Ghiringhelli

Uncertainty-quantification methods are applied to estimate the confidence of deep-neural-networks classifiers over their predictions. However, most widely used methods are known to be overconfident. We address this problem by developing an algorithm that exploits the latent-space representation of data points fed into the network, to assess the accuracy of their prediction.