Synthetic-domain Neural Networks using Integrated Nonlinear Phononics on Lithium Niobate
Leveraging strong second-order nonlinearities of lithium niobate, we demonstrate synthetic-domain neural networks with both efficient linear and nonlinear operations. A high accuracy of 98.2% is experimentally achieved for a four-class classification task.
Authors
- Wenjie Xiong (ORCID: https://orcid.org/0000-0002-7626-2651)
- Bernadeta Srijanto (ORCID: https://orcid.org/0000-0002-1188-1267)
- Linbo Shao (ORCID: https://orcid.org/0000-0002-0615-7848)
- Ivan I. Kravchenko (ORCID: https://orcid.org/0000-0003-4999-5822)
- Yizheng Zhu (ORCID: https://orcid.org/0000-0001-8099-0371)
- Joseph G. Thomas (ORCID: https://orcid.org/0000-0002-3682-5931)
- Ming Jin (ORCID: https://orcid.org/0000-0002-0170-7281)
- Jun Ji (ORCID: https://orcid.org/0000-0002-6994-5358)
- Zichen Xi
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1364/cleo_si.2025.ss103_3
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00