Applying artificial neural networks to coherent control experiments: A theoretical proof of concept

Esben F. Thomas, Niels E. Henriksen*

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

152 Downloads (Pure)

Abstract

We propose a method of experimental coherent control that exploits partial and/or prior knowledge of a molecular system to efficiently arrive at a solution by using an artificial neural network (ANN) to generate a control field in consecutive temporal steps based on dynamic experimental feedback. Using a one-dimensional double-well potential model corresponding to the torsional motion of 3,5-difluoro-3′,5′-dibromobiphenyl (F2H3C6-C6H3Br2) to outline and verify our approach, we theoretically demonstrate that an optimized ANN can achieve robust quantum control of nuclear wave-packet transfer between wells despite the addition of random perturbations to the simulated molecular potential energy and polarizability surfaces. We suggest that under certain conditions this will also allow the ANN to achieve the stated control objective in an experimental situation. We show that the number of measurements our method requires to generate an optimized field is equal to the dimensionality of the optimization problem, which is significantly less than a naive closed-loop approach would generally need to achieve the same results.

Original languageEnglish
Article number023422
JournalPhysical Review A
Volume99
Issue number2
Number of pages12
ISSN2469-9926
DOIs
Publication statusPublished - 2019

Cite this

@article{27c21c1f36da49668bab0444eca7a5f6,
title = "Applying artificial neural networks to coherent control experiments: A theoretical proof of concept",
abstract = "We propose a method of experimental coherent control that exploits partial and/or prior knowledge of a molecular system to efficiently arrive at a solution by using an artificial neural network (ANN) to generate a control field in consecutive temporal steps based on dynamic experimental feedback. Using a one-dimensional double-well potential model corresponding to the torsional motion of 3,5-difluoro-3′,5′-dibromobiphenyl (F2H3C6-C6H3Br2) to outline and verify our approach, we theoretically demonstrate that an optimized ANN can achieve robust quantum control of nuclear wave-packet transfer between wells despite the addition of random perturbations to the simulated molecular potential energy and polarizability surfaces. We suggest that under certain conditions this will also allow the ANN to achieve the stated control objective in an experimental situation. We show that the number of measurements our method requires to generate an optimized field is equal to the dimensionality of the optimization problem, which is significantly less than a naive closed-loop approach would generally need to achieve the same results.",
author = "Thomas, {Esben F.} and Henriksen, {Niels E.}",
year = "2019",
doi = "10.1103/PhysRevA.99.023422",
language = "English",
volume = "99",
journal = "Physical Review A (Atomic, Molecular and Optical Physics)",
issn = "2469-9926",
publisher = "American Physical Society",
number = "2",

}

Applying artificial neural networks to coherent control experiments: A theoretical proof of concept. / Thomas, Esben F.; Henriksen, Niels E.

In: Physical Review A, Vol. 99, No. 2, 023422, 2019.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Applying artificial neural networks to coherent control experiments: A theoretical proof of concept

AU - Thomas, Esben F.

AU - Henriksen, Niels E.

PY - 2019

Y1 - 2019

N2 - We propose a method of experimental coherent control that exploits partial and/or prior knowledge of a molecular system to efficiently arrive at a solution by using an artificial neural network (ANN) to generate a control field in consecutive temporal steps based on dynamic experimental feedback. Using a one-dimensional double-well potential model corresponding to the torsional motion of 3,5-difluoro-3′,5′-dibromobiphenyl (F2H3C6-C6H3Br2) to outline and verify our approach, we theoretically demonstrate that an optimized ANN can achieve robust quantum control of nuclear wave-packet transfer between wells despite the addition of random perturbations to the simulated molecular potential energy and polarizability surfaces. We suggest that under certain conditions this will also allow the ANN to achieve the stated control objective in an experimental situation. We show that the number of measurements our method requires to generate an optimized field is equal to the dimensionality of the optimization problem, which is significantly less than a naive closed-loop approach would generally need to achieve the same results.

AB - We propose a method of experimental coherent control that exploits partial and/or prior knowledge of a molecular system to efficiently arrive at a solution by using an artificial neural network (ANN) to generate a control field in consecutive temporal steps based on dynamic experimental feedback. Using a one-dimensional double-well potential model corresponding to the torsional motion of 3,5-difluoro-3′,5′-dibromobiphenyl (F2H3C6-C6H3Br2) to outline and verify our approach, we theoretically demonstrate that an optimized ANN can achieve robust quantum control of nuclear wave-packet transfer between wells despite the addition of random perturbations to the simulated molecular potential energy and polarizability surfaces. We suggest that under certain conditions this will also allow the ANN to achieve the stated control objective in an experimental situation. We show that the number of measurements our method requires to generate an optimized field is equal to the dimensionality of the optimization problem, which is significantly less than a naive closed-loop approach would generally need to achieve the same results.

U2 - 10.1103/PhysRevA.99.023422

DO - 10.1103/PhysRevA.99.023422

M3 - Journal article

VL - 99

JO - Physical Review A (Atomic, Molecular and Optical Physics)

JF - Physical Review A (Atomic, Molecular and Optical Physics)

SN - 2469-9926

IS - 2

M1 - 023422

ER -