Multiparameter optimisation of a magneto-optical trap using deep learning.

Autor:	Tranter AD; Centre for Quantum Computation and Communication Technologies, Department of Quantum Science, Research School of Physics and Engineering, The Australian National University, Acton, 2601, Australia., Slatyer HJ; Centre for Quantum Computation and Communication Technologies, Department of Quantum Science, Research School of Physics and Engineering, The Australian National University, Acton, 2601, Australia., Hush MR; School of Engineering and Information Technology, University of New South Wales, Canberra, 2600, Australia., Leung AC; Centre for Quantum Computation and Communication Technologies, Department of Quantum Science, Research School of Physics and Engineering, The Australian National University, Acton, 2601, Australia., Everett JL; Centre for Quantum Computation and Communication Technologies, Department of Quantum Science, Research School of Physics and Engineering, The Australian National University, Acton, 2601, Australia., Paul KV; Centre for Quantum Computation and Communication Technologies, Department of Quantum Science, Research School of Physics and Engineering, The Australian National University, Acton, 2601, Australia., Vernaz-Gris P; Centre for Quantum Computation and Communication Technologies, Department of Quantum Science, Research School of Physics and Engineering, The Australian National University, Acton, 2601, Australia., Lam PK; Centre for Quantum Computation and Communication Technologies, Department of Quantum Science, Research School of Physics and Engineering, The Australian National University, Acton, 2601, Australia., Buchler BC; Centre for Quantum Computation and Communication Technologies, Department of Quantum Science, Research School of Physics and Engineering, The Australian National University, Acton, 2601, Australia. ben.buchler@anu.edu.au., Campbell GT; Centre for Quantum Computation and Communication Technologies, Department of Quantum Science, Research School of Physics and Engineering, The Australian National University, Acton, 2601, Australia.
Jazyk:	angličtina
Zdroj:	Nature communications [Nat Commun] 2018 Oct 19; Vol. 9 (1), pp. 4360. Date of Electronic Publication: 2018 Oct 19.
DOI:	10.1038/s41467-018-06847-1
Abstrakt:	Machine learning based on artificial neural networks has emerged as an efficient means to develop empirical models of complex systems. Cold atomic ensembles have become commonplace in laboratories around the world, however, many-body interactions give rise to complex dynamics that preclude precise analytic optimisation of the cooling and trapping process. Here, we implement a deep artificial neural network to optimise the magneto-optic cooling and trapping of neutral atomic ensembles. The solution identified by machine learning is radically different to the smoothly varying adiabatic solutions currently used. Despite this, the solutions outperform best known solutions producing higher optical densities.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu