Skip to content Skip to navigation
University of Warwick
  • Study
  • |
  • Research
  • |
  • Business
  • |
  • Alumni
  • |
  • News
  • |
  • About

University of Warwick
Publications service & WRAP

Highlight your research

  • WRAP
    • Home
    • Search WRAP
    • Browse by Warwick Author
    • Browse WRAP by Year
    • Browse WRAP by Subject
    • Browse WRAP by Department
    • Browse WRAP by Funder
    • Browse Theses by Department
  • Publications Service
    • Home
    • Search Publications Service
    • Browse by Warwick Author
    • Browse Publications service by Year
    • Browse Publications service by Subject
    • Browse Publications service by Department
    • Browse Publications service by Funder
  • Help & Advice
University of Warwick

The Library

  • Login
  • Admin

Adaptive partial scanning transmission electron microscopy with reinforcement learning

Tools
- Tools
+ Tools

Ede, Jeffrey M. (2020) Adaptive partial scanning transmission electron microscopy with reinforcement learning. Working Paper. Cornell University: arXiv. (Submitted)

[img]
Preview
PDF
WRAP-Adaptive-partial-scanning-transmission-electron-2021.pdf - Submitted Version - Requires a PDF viewer.

Download (1856Kb) | Preview
[img]
Preview
PDF
adaptive_scans_supplementary.pdf - Supplemental Material - Requires a PDF viewer.

Download (3841Kb) | Preview
Official URL: https://arxiv.org/abs/2004.02786

Request Changes to record.

Abstract

Compressed sensing can decrease scanning transmission electron microscopy electron dose and scan time with minimal information loss. Traditionally, sparse scans used in compressed sensing sample a static set of probing locations. In contrast, we present a prototype for a contiguous sparse scan system that piecewise adapts scan paths to specimens as they are scanned. Sampling directions for scan segments are chosen by a recurrent neural network based on previously observed scan segments. The recurrent actor is trained by reinforcement learning to cooperate with a feedforward convolutional neural network that completes sparse scans. This paper presents our learning policy, experiments, and example partial scans, and discusses future research directions. Source code, pretrained models, and training data is openly accessible at https://github.com/Jeffrey-Ede/adaptive-scans.

Item Type: Working or Discussion Paper (Working Paper)
Subjects: Q Science > Q Science (General)
Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
Q Science > QC Physics
Q Science > QH Natural history
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Faculty of Science > Physics
Library of Congress Subject Headings (LCSH): Compressed sensing (Telecommunication), Machine learning, Electron microscopy , Reinforcement learning , Scanning transmission electron microscopy
Publisher: arXiv
Place of Publication: Cornell University
Official Date: 22 December 2020
Dates:
DateEvent
22 December 2020Submitted
Number of Pages: 12
Institution: University of Warwick
Status: Peer Reviewed
Publication Status: Submitted
Copyright Holders: Jeffrey M. Ede
RIOXX Funder/Project Grant:
Project/Grant IDRIOXX Funder NameFunder ID
EP/N035437/1[EPSRC] Engineering and Physical Sciences Research Councilhttp://dx.doi.org/10.13039/501100000266
Studentship 1917382[EPSRC] Engineering and Physical Sciences Research Councilhttp://dx.doi.org/10.13039/501100000266
Open Access Version:
  • ArXiv

Request changes or add full text files to a record

Repository staff actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics

twitter

Email us: wrap@warwick.ac.uk
Contact Details
About Us