EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Probe microscopy is all you need *

Sergei V Kalinin, Rama Vasudevan, Yongtao Liu, Ayana Ghosh, Kevin Roccapriore, Maxim Ziatdinov

Machine Learning: Science and Technology · 01.06.2023 · 4 (2) · 023001

DOI: 10.1088/2632-2153/acccd5 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning: Science and Technology, online erschienen am 22.05.2023. Verfasst von Sergei V Kalinin und 5 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 231 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We pose that microscopy offers an ideal real-world experimental environment for the development and deployment of active Bayesian and reinforcement learning methods. Indeed, the tremendous progress achieved by machine learning (ML) and artificial intelligence over the last decade has been largely achieved via the utilization of static data sets, from the paradigmatic MNIST to the bespoke corpora of text and image data used to train large models such as GPT3, DALL·E and others. However, it is now recognized that continuous, minute improvements to state-of-the-art do not necessarily translate to advances in real-world applications. We argue that a promising pathway for the development of ML methods is via the route of domain-specific deployable algorithms in areas such as electron and scanning probe microscopy and chemical imaging. This will benefit both fundamental physical studies and serve as a test bed for more complex autonomous systems such as robotics and manufacturing. Favorable environment characteristics of scanning and electron microscopy include low risk, extensive availability of domain-specific priors and rewards, relatively small effects of exogenous variables, and often the presence of both upstream first principles as well as downstream learnable physical models for both statics and dynamics. Recent developments in programmable interfaces, edge computing, and access to application programming interfaces (APIs) facilitating microscope control, all render the deployment of ML codes on operational microscopes straightforward. We discuss these considerations and hope that these arguments will lead to create novel set of development targets for the ML community by accelerating both real world ML applications and scientific progress.

Zitieren

APA

Kalinin, S. V., Vasudevan, R., Liu, Y., Ghosh, A., Roccapriore, K., & Ziatdinov, M. (2023). Probe microscopy is all you need *. Machine Learning: Science and Technology, 4(2), 023001. https://doi.org/10.1088/2632-2153/acccd5

Vancouver

Kalinin SV, Vasudevan R, Liu Y, Ghosh A, Roccapriore K, Ziatdinov M. Probe microscopy is all you need *. Machine Learning: Science and Technology. 2023;4(2):023001. doi:10.1088/2632-2153/acccd5

BibTeX
@article{Kalinin2023,
  author = {Kalinin, Sergei V and Vasudevan, Rama and Liu, Yongtao and Ghosh, Ayana and Roccapriore, Kevin and Ziatdinov, Maxim},
  title = {Probe microscopy is all you need *},
  journal = {Machine Learning: Science and Technology},
  year = {2023},
  volume = {4},
  number = {2},
  pages = {023001},
  doi = {10.1088/2632-2153/acccd5}
}
Kostenlos starten →