Equivariant Neural Networks for Controlling Dynamic Spatial Light Modulators
Name
40192_2024_383_ReferencePDF.pdf
Size
1.29 MB
Format
Adobe PDF
Checksum (MD5)
f7bdab20247ebd35aaafbfd7574325ef
Author(s)
Vasisht Shankar, Sumukh
Wang, Rui
D’Souza, Darrel
Singer, Jonathan P.
Walters, Robin
Date Issued
November 22, 2024
Journal
Integrating Materials and Manufacturing Innovation
Publisher
Springer International Publishing
Citation
Vasisht Shankar, S., Wang, R., D’Souza, D. et al. Equivariant Neural Networks for Controlling Dynamic Spatial Light Modulators. Integr Mater Manuf Innov 13, 857–865 (2024).
Version
Author's final manuscript
Abstract
Spatial light modulators (SLMs) are devices that are capable of manipulating incident light by passing it through an array of phase/intensity altering pixels. A recent alternative design involves creating a phase mask by directing a thin film of fluid with thermocapillary forces generated by a controlled temperature map. However, it is difficult to determine the input temperature signal necessary to induce a given height profile. The relationship between temperature and height is given by the thin film equation, a fourth-order nonlinear PDE, which is difficult to solve numerically. To address this problem, we train deep neural networks to directly solve the inverse problem, mapping from the desired height profiles to the needed temperature patterns. We design novel equivariant networks incorporating scale and rotation symmetry of the underlying thin film equation. We demonstrate the effectiveness of equivariant models for learning the complex relationship between input temperature signals and the resulting light patterns, showing they are more accurate than non-equivariant baselines and very computationally efficient. This work has implications for a range of applications, including high-power laser systems, and could lead to more efficient and effective ways to deploy the process of modulation of light in SLMs in a variety of applications.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s40192-024-00383-1
