TR2022-046
AutoML Hyperparameter Tuning of Generative DNN Architecture for Nanophotonic Device Design
-
- , "AutoML Hyperparameter Tuning of Generative DNN Architecture for Nanophotonic Device Design", Conference on Lasers and Electro-Optics (CLEO), DOI: 10.1364/CLEO_AT.2022.JW3A.44, May 2022.BibTeX TR2022-046 PDF Presentation
- @inproceedings{Koike-Akino2022may3,
- author = {Koike-Akino, Toshiaki and Kojima, Keisuke and Wang, Ye},
- title = {{AutoML Hyperparameter Tuning of Generative DNN Architecture for Nanophotonic Device Design}},
- booktitle = {Conference on Lasers and Electro-Optics (CLEO)},
- year = 2022,
- month = may,
- publisher = {Optica},
- doi = {10.1364/CLEO_AT.2022.JW3A.44},
- isbn = {978-1-957171-05-0},
- url = {https://www.merl.com/publications/TR2022-046}
- }
- , "AutoML Hyperparameter Tuning of Generative DNN Architecture for Nanophotonic Device Design", Conference on Lasers and Electro-Optics (CLEO), DOI: 10.1364/CLEO_AT.2022.JW3A.44, May 2022.
-
MERL Contacts:
-
Research Areas:
Artificial Intelligence, Electronic and Photonic Devices, Machine Learning, Optimization, Signal Processing
Abstract:
We introduce an automated machine learning (AutoML) framework to construct a deep neural network model relevant for inverse design of nanophotonic devices without relying on manual trial-and-error hyperparameter tuning.