Automatized convergence of optoelectronic simulations using active machine learning

Bertrand Rouet-Leduc; Claudia Hulbert; Kipton Barros; Turab Lookman; Colin J. Humphreys

doi:10.1063/1.4996233

Automatized convergence of optoelectronic simulations using active machine learning

Bertrand Rouet-Leduc
, Claudia Hulbert
, Kipton Barros
, Turab Lookman
, Colin J. Humphreys

Research output: Contribution to journal › Article › peer-review

12 Scopus citations

Abstract

A fundamental problem of optoelectronic simulations is to achieve convergence. We use statistical analysis and machine learning to effectively guide the selection of the next device to be examined based upon the expected convergence of the simulation. This active learning strategy rapidly constructs a model that predicts Poisson-Schrdinger simulations of devices and that simultaneously produces fully converged simulations.

Original language	English
Article number	043506
Journal	Applied Physics Letters
Volume	111
Issue number	4
DOIs	https://doi.org/10.1063/1.4996233
State	Published - 24 Jul 2017
Externally published	Yes

Access to Document

10.1063/1.4996233

Cite this

@article{a7695a8aaeb844b0914794290fd148e8,

title = "Automatized convergence of optoelectronic simulations using active machine learning",

abstract = "A fundamental problem of optoelectronic simulations is to achieve convergence. We use statistical analysis and machine learning to effectively guide the selection of the next device to be examined based upon the expected convergence of the simulation. This active learning strategy rapidly constructs a model that predicts Poisson-Schrdinger simulations of devices and that simultaneously produces fully converged simulations.",

author = "Bertrand Rouet-Leduc and Claudia Hulbert and Kipton Barros and Turab Lookman and Humphreys, \{Colin J.\}",

note = "Publisher Copyright: {\textcopyright} 2017 Author(s).",

year = "2017",

month = jul,

day = "24",

doi = "10.1063/1.4996233",

language = "英语",

volume = "111",

journal = "Applied Physics Letters",

issn = "0003-6951",

publisher = "American Institute of Physics",

number = "4",

}

TY - JOUR

T1 - Automatized convergence of optoelectronic simulations using active machine learning

AU - Rouet-Leduc, Bertrand

AU - Hulbert, Claudia

AU - Barros, Kipton

AU - Lookman, Turab

AU - Humphreys, Colin J.

PY - 2017/7/24

Y1 - 2017/7/24

N2 - A fundamental problem of optoelectronic simulations is to achieve convergence. We use statistical analysis and machine learning to effectively guide the selection of the next device to be examined based upon the expected convergence of the simulation. This active learning strategy rapidly constructs a model that predicts Poisson-Schrdinger simulations of devices and that simultaneously produces fully converged simulations.

AB - A fundamental problem of optoelectronic simulations is to achieve convergence. We use statistical analysis and machine learning to effectively guide the selection of the next device to be examined based upon the expected convergence of the simulation. This active learning strategy rapidly constructs a model that predicts Poisson-Schrdinger simulations of devices and that simultaneously produces fully converged simulations.

UR - https://www.scopus.com/pages/publications/85026370485

U2 - 10.1063/1.4996233

DO - 10.1063/1.4996233

M3 - 文章

AN - SCOPUS:85026370485

SN - 0003-6951

VL - 111

JO - Applied Physics Letters

JF - Applied Physics Letters

IS - 4

M1 - 043506

ER -

Automatized convergence of optoelectronic simulations using active machine learning

Abstract

Access to Document

Other files and links

Fingerprint

Cite this