Conference paper
Attention Mechanisms for Broadband Feature Prediction for Electromagnetic and Photonic Applications
Proceedings of SPIE, the international society for optical engineering, 126750
01 Jan 2023
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
We present a study on the accuracy of three neural network architectures, namely fully-connected neural networks, recurrent neural networks, and attention-based neural networks, in predicting the coupling response of broadband microresonator frequency combs. These frequency combs are crucial for technologies like optical atomic clocks. Optimizing their spectral features, especially the dispersion in coupling to an access waveguide, can be computationally demanding due to the large number of parameters and wide spectral bandwidths involved. To address this challenge, we employ machine learning algorithms to estimate the coupling response at wavelengths not present in the input training data. Our findings demonstrate that when trained with data sets encompassing the upper and lower limits of each design feature, attention mechanisms achieve over 90% accuracy in predicting the coupling rate for spectral ranges six times wider than those used in training. This significantly reduces the computational burden for numerical optimization in ring resonator design, potentially leading to a six-fold reduction in compute time. Moreover, devices with strong correlations between design features and performance metrics may experience even greater acceleration.
Metrics
11 Record Views
Details
- Title
- Attention Mechanisms for Broadband Feature Prediction for Electromagnetic and Photonic Applications
- Creators
- Ergun Simsek - University of Maryland, Baltimore CountyMasoud Soroush - Drexel University, Chemical and Biological EngineeringGregory Moille - National Institute of Standards and TechnologyKartik Srinivasan - National Institute of Standards and TechnologyCurtis R. Menyuk - University of Maryland, Baltimore County
- Publication Details
- Proceedings of SPIE, the international society for optical engineering, 126750
- Series
- Proceedings of SPIE; 12675
- Publisher
- SPIE
- Number of pages
- 6
- Grant note
- NIST-on-a-chip DARPA APHI programs FA9550-19-S-0003 / AFOSR grant; United States Department of Defense; Air Force Office of Scientific Research (AFOSR)
- Resource Type
- Conference paper
- Language
- English
- Academic Unit
- Chemical and Biological Engineering
- Web of Science ID
- WOS:001259432500009
- Scopus ID
- 2-s2.0-85197216421
- Other Identifier
- 991022005883404721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Interdisciplinary Applications
- Computer Science, Theory & Methods