Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.18047 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914372670980096 |
|---|---|
| author | Anteneh, Amanuel Kim, Kyungeun Schwarz, J. M. Klich, Israel Pfister, Olivier |
| author_facet | Anteneh, Amanuel Kim, Kyungeun Schwarz, J. M. Klich, Israel Pfister, Olivier |
| contents | We present a method for implementing an optical neural network using only linear optical resources, namely field displacement and interferometry applied to coherent states of light. The nonlinearity required for learning in a neural network is realized via an encoding of the input into phase shifts allowing for far more straightforward experimental implementation compared to previous proposals for, and demonstrations of, $\textit{in situ}$ inference. Beyond $\textit{in situ}$ inference, the method enables $\textit{in situ}$ training by utilizing established techniques like parameter shift methods or physical backpropagation to extract gradients directly from measurements of the linear optical circuit. We also investigate the effect of photon losses and find the model to be very resilient to these. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18047 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Laser interferometry as a robust neuromorphic platform for machine learning Anteneh, Amanuel Kim, Kyungeun Schwarz, J. M. Klich, Israel Pfister, Olivier Optics Emerging Technologies Machine Learning We present a method for implementing an optical neural network using only linear optical resources, namely field displacement and interferometry applied to coherent states of light. The nonlinearity required for learning in a neural network is realized via an encoding of the input into phase shifts allowing for far more straightforward experimental implementation compared to previous proposals for, and demonstrations of, $\textit{in situ}$ inference. Beyond $\textit{in situ}$ inference, the method enables $\textit{in situ}$ training by utilizing established techniques like parameter shift methods or physical backpropagation to extract gradients directly from measurements of the linear optical circuit. We also investigate the effect of photon losses and find the model to be very resilient to these. |
| title | Laser interferometry as a robust neuromorphic platform for machine learning |
| topic | Optics Emerging Technologies Machine Learning |
| url | https://arxiv.org/abs/2601.18047 |