2022
DOI: 10.3389/fmats.2021.772014
|View full text |Cite
|
Sign up to set email alerts
|

Benchmarking Autonomous Scattering Experiments Illustrated on TAS

Abstract: With the advancement of artificial intelligence and machine learning methods, autonomous approaches are recognized to have great potential for performing more efficient scattering experiments. In our view, it is crucial for such approaches to provide thorough evidence about respective performance improvements in order to increase acceptance within a scientific community. Therefore, we propose a benchmarking procedure designed as a cost-benefit analysis that is applicable to any scattering method sequentially c… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
5
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5
1

Relationship

1
5

Authors

Journals

citations
Cited by 6 publications
(5 citation statements)
references
References 16 publications
0
5
0
Order By: Relevance
“…We briefly describe its setting in the following paragraph. For more details, we refer to the original work 34 .…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…We briefly describe its setting in the following paragraph. For more details, we refer to the original work 34 .…”
Section: Resultsmentioning
confidence: 99%
“…The benchmark results can be reproduced by using code from the repository jugit.fz-juelich.de/ainx/base-fork-ariane (commit SHA: 3715a772 ). It is a fork, adjusted to our approach, of the benchmark API from jugit.fz-juelich.de/ainx/base which is part of the mentioned original work on the benchmarking procedure 34 .…”
mentioning
confidence: 99%
“…Higher measurement efficiency will lead to shorter measurement times and opportunities for additional experiments. Improving the speed of X-ray and neutron measurements with AL (Noack et al, 2019(Noack et al, , 2020McDannald et al, 2022;Teixeira Parente et al, 2023) is thus very much needed.…”
Section: Introductionmentioning
confidence: 99%
“…Alternate approaches, such as Bayesian Optimization (BO) based Gaussian process (GP) regression [16] have also been used since these do not require any training data unlike the supervised learning approaches. Recent demonstrations for small-angle x-ray scattering [17], scanning probe microscopy [18] and neutron triple axis spectrometry [19] further highlight the potential of such methods.…”
Section: Introductionmentioning
confidence: 99%