Minimal memory differentiable FDTD for inverse design
Conference on Lasers and Electro-Optics（2022）
Abstract
We construct a reverse mode automatic differentiation FDTD that reduces the memory requirement, a typical bottleneck, by two orders of magnitude, and employ it to produce meta-atoms with specified phase responses and group delays.
MoreTranslated text
Key words
minimal memory differentiable FDTD,inverse design,reverse mode automatic differentiation FDTD,memory requirement,typical bottleneck,group delays,phase responses
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined