Reinforcement learning for adaptive sampling in X-ray applications
Abstract/Contents
- Abstract
- We propose adaptive sampling algorithms for automating image sampling in scientific x-ray applications. In these applications, we query measurements from various functions of an image in order to estimate it. Since collecting samples is expensive both in terms of time, human resources, and the cost of operating machinery, our goal is to produce autonomous, adaptive sampling methods that attempt to optimize some tradeoff between cost and quality of image estimation, based on information gained from previous measurements. In order to accomplish this, we propose a general methodology that uses reinforcement learning to train autonomous, image-sampling policies that optimize our objective.
Description
| Type of resource | text |
|---|---|
| Form | electronic resource; remote; computer; online resource |
| Extent | 1 online resource. |
| Place | California |
| Place | [Stanford, California] |
| Publisher | [Stanford University] |
| Copyright date | 2022; ©2022 |
| Publication date | 2022; 2022 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Author | Betterton, Jean-Raymond Melingui |
|---|---|
| Degree supervisor | Brunskill, Emma |
| Degree supervisor | Kochenderfer, Mykel J, 1980- |
| Thesis advisor | Brunskill, Emma |
| Thesis advisor | Kochenderfer, Mykel J, 1980- |
| Thesis advisor | Ahmadipouranari, Nima |
| Thesis advisor | Wetzstein, Gordon |
| Degree committee member | Ahmadipouranari, Nima |
| Degree committee member | Wetzstein, Gordon |
| Associated with | Stanford University, Computer Science Department |
Subjects
| Genre | Theses |
|---|---|
| Genre | Text |
Bibliographic information
| Statement of responsibility | Jean-Raymond Betterton. |
|---|---|
| Note | Submitted to the Computer Science Department. |
| Thesis | Thesis Ph.D. Stanford University 2022. |
| Location | https://purl.stanford.edu/bd640pm2612 |
Access conditions
- Copyright
- © 2022 by Jean-Raymond Melingui Betterton
- License
- This work is licensed under a Creative Commons Attribution 3.0 Unported license (CC BY).
Also listed in
Loading usage metrics...