An MZI-Based Block Optical Neural Network Based on LDU Structure
We propose an LDU-based block optical neural network, significantly reducing hardware complexity and improving matrix mapping fidelity. It achieves 90.47% accuracy on SVHN dataset and maintains 80.84% under hardware errors, demonstrating effectiveness and exceptional robustness.
Authors
- Kun Xu (ORCID: https://orcid.org/0000-0002-1663-9998)
- Dewei Wang (ORCID: https://orcid.org/0000-0002-0357-3248)
- Qi Chen (ORCID: https://orcid.org/0000-0002-7430-1645)
- Tian Zhang (ORCID: https://orcid.org/0000-0002-1284-1232)
- Jian Dai (ORCID: https://orcid.org/0000-0002-0486-0628)
- Zhenzhen Cai (ORCID: https://orcid.org/0000-0003-4831-8897)
Institutions
- Beijing University of Posts and Telecommunications (CN)
- State Key Laboratory of Information Photonics and Optical Communications
Publication Details
- Published
- 2025-06-29
- DOI
- https://doi.org/10.23919/oecc/psc62146.2025.11109193
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00