Abstract The popularization of Machine Learning (ML) and the advent of Noisy Intermediate-Scale Quantum (NISQ) devices for Quantum Computing (QC) sparked new inspiration for the search for techniques reducing computation time in mechanics. We evaluate artificial neural networks (ANNs) as candidates for creating computationally fast surrogate models for otherwise time-consuming simulations, using a multiscale and multiphase model describing processes in the human liver. We also give a short overview of interesting quantum-enhanced algorithms capable of reducing computational cost in parts of complex simulations.
%0 Journal Article
%1 doi:10.1002/pamm.201900470
%A Mielke, André
%A Ricken, Tim
%D 2019
%J PAMM
%K ANN myown quantum_computing
%N 1
%P e201900470
%R 10.1002/pamm.201900470
%T Evaluating Artificial Neural Networks and Quantum Computing for Mechanics
%U https://onlinelibrary.wiley.com/doi/abs/10.1002/pamm.201900470
%V 19
%X Abstract The popularization of Machine Learning (ML) and the advent of Noisy Intermediate-Scale Quantum (NISQ) devices for Quantum Computing (QC) sparked new inspiration for the search for techniques reducing computation time in mechanics. We evaluate artificial neural networks (ANNs) as candidates for creating computationally fast surrogate models for otherwise time-consuming simulations, using a multiscale and multiphase model describing processes in the human liver. We also give a short overview of interesting quantum-enhanced algorithms capable of reducing computational cost in parts of complex simulations.
@article{doi:10.1002/pamm.201900470,
abstract = {Abstract The popularization of Machine Learning (ML) and the advent of Noisy Intermediate-Scale Quantum (NISQ) devices for Quantum Computing (QC) sparked new inspiration for the search for techniques reducing computation time in mechanics. We evaluate artificial neural networks (ANNs) as candidates for creating computationally fast surrogate models for otherwise time-consuming simulations, using a multiscale and multiphase model describing processes in the human liver. We also give a short overview of interesting quantum-enhanced algorithms capable of reducing computational cost in parts of complex simulations.},
added-at = {2020-02-18T20:56:08.000+0100},
author = {Mielke, André and Ricken, Tim},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/2168c06dafca05699c31c2f2f66f4a97f/timricken},
doi = {10.1002/pamm.201900470},
eprint = {https://onlinelibrary.wiley.com/doi/pdf/10.1002/pamm.201900470},
interhash = {e431f2583693313af435e39c2a95a518},
intrahash = {168c06dafca05699c31c2f2f66f4a97f},
journal = {PAMM},
keywords = {ANN myown quantum_computing},
number = 1,
pages = {e201900470},
timestamp = {2020-02-18T19:56:08.000+0100},
title = {Evaluating Artificial Neural Networks and Quantum Computing for Mechanics},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/pamm.201900470},
volume = 19,
year = 2019
}
