Abstract
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.
| Original language | English |
|---|---|
| Title of host publication | 2025 Conference on Lasers and Electro-Optics, CLEO 2025 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Electronic) | 9781957171500 |
| State | Published - 2025 |
| Event | 2025 Conference on Lasers and Electro-Optics, CLEO 2025 - Long Beach, United States Duration: May 4 2025 → May 9 2025 |
Publication series
| Name | 2025 Conference on Lasers and Electro-Optics, CLEO 2025 |
|---|
Conference
| Conference | 2025 Conference on Lasers and Electro-Optics, CLEO 2025 |
|---|---|
| Country/Territory | United States |
| City | Long Beach |
| Period | 05/4/25 → 05/9/25 |
Funding
Device fabrication and SEM were conducted as part of user projects (CNMS2022-B-01473, CNMS2024-B-02643) at the Center for Nanophase Materials Sciences, which is a DOE Office of Science User Facility. Research was sponsored by the Air Force Office of Scientific Research (AFOSR) under W911NF-23-1-0235 and FA9550-22-1-0548 and by Commonwealth Cybersecurity Initiative. The views and conclusions contained in this document are those of the authors and do not necessarily reflect the position or the policy of the United States Government. No official endorsement should be inferred.