Power-Efficient Optical Convolutional Binary Neural Network Processors by Dual Ring Assisted MZIs
We present a power-efficient optical convolutional binary neural network processor utilizing dual ring assisted Mach-Zehnder interferometers. Numerical simulations demonstrate a prediction accuracy of 91%, accompanied by a thorough analysis of the performance of the processor.
Authors
- Yu Jian Cheng (ORCID: https://orcid.org/0000-0003-1075-4167)
- Ruoyun Yao (ORCID: https://orcid.org/0000-0002-4321-5584)
- Jinhua Chen (ORCID: https://orcid.org/0000-0003-4801-3233)
- Chen Ji
- Weiwei Pan (ORCID: https://orcid.org/0000-0001-8323-861X)
Institutions
- Zhejiang A & F University (CN)
- Zhejiang University (CN)
Publication Details
- Published
- 2025-06-29
- DOI
- https://doi.org/10.23919/oecc/psc62146.2025.11109904
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00