Photonic network-in-network with on-chip optical diffraction to enable high-order tensor inputs
We present a photonic network-in-network architecture integrating an on-chip diffractive optical neural network for parallel tensor fusion and channel-wise pooling, reducing back-end parameters by 55.16% while maintaining competitive performance in machine vision over benchmark datasets.
Authors
- Wencan Liu (ORCID: https://orcid.org/0009-0009-8937-6293)
- Sigang Yang (ORCID: https://orcid.org/0000-0002-2209-287X)
- Peter Chan (ORCID: https://orcid.org/0000-0002-5720-0199)
- Hongwei Chen (ORCID: https://orcid.org/0000-0002-9400-6053)
- Yuyao Huang (ORCID: https://orcid.org/0000-0002-3989-9514)
- Run Cang Sun
Institutions
- Beijing Institute of Technology (CN)
- Tsinghua University (CN)
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1364/cleo_si.2025.ss169_4
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00