Document type
ArticleVersion
Published versionPublication date
Publication license
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/195455
Supervised learning of few dirty bosons with variable particle number
Journal Title
Director/Tutor
Journal ISSN
Volume Title
Related resource
Abstract
We investigate the supervised machine learning of few interacting bosons in optical speckle disorder via artificial neural networks. The learning curve shows an approximately universal power-law scaling for different particle numbers and for different interaction strengths. We introduce a network architecture that can be trained and tested on heterogeneous datasets including different particle numbers. This network provides accurate predictions for all system sizes included in the training set and, by design, is suitable to attempt extrapolations to (computationally challenging) larger sizes. Notably, a novel transfer-learning strategy is implemented, whereby the learning of the larger systems is substantially accelerated and made consistently accurate by including in the training set many small-size instances.
Subject
Subject (English)
Citation
Citation
MUJAL TORREBLANCA, Pere, et al. Supervised learning of few dirty bosons with variable particle number. SciPost Physics. 2021. Vol. 10, num. 3, pags. 73-89. ISSN 2542-4653. [consulted: 14 of August of 2026]. Available at: https://hdl.handle.net/2445/195455