Supervised learning of few dirty bosons with variable particle number
Open Access
- 24 March 2021
- journal article
- research article
- Published by Stichting SciPost in SciPost Physics
- Vol. 10 (3) , 073
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.Keywords
All Related Versions
Funding Information
- European Commission (FIS2017-87534-P)
- Generalitat de Catalunya (001-P-001644)
- Ministero dell’Istruzione, dell’Università e della Ricerca (20172H2SC4)
This publication has 44 references indexed in Scilit:
- A machine learning approach to predicting protein–ligand binding affinity with applications to molecular dockingBioinformatics, 2010
- Weakly interacting Bose gas in a random environmentPhysical Review B, 2009
- Anderson localization of a non-interacting Bose–Einstein condensateNature, 2008
- Ultracold Bose Gases in 1D Disorder: From Lifshits Glass to Bose-Einstein CondensatePhysical Review Letters, 2007
- Generalized Neural-Network Representation of High-Dimensional Potential-Energy SurfacesPhysical Review Letters, 2007
- Collective dynamics and expansion of a Bose-Einstein condensate in a random potentialPhysical Review A, 2006
- A Numerical Study on Learning Curves in Stochastic Multilayer Feedforward NetworksNeural Computation, 1996
- Speckle photography fringe analysis: assessment of current algorithmsApplied Optics, 1989
- Boson localization and the superfluid-insulator transitionPhysical Review B, 1989
- On the approximate realization of continuous mappings by neural networksNeural Networks, 1989