Online unsupervised Hebbian learning in deep photonic neuromorphic networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914374300467200 |
|---|---|
| author | Li, Xi Biswas, Disha Zhou, Peng Brigner, Wesley H. Capuano, Anna Friedman, Joseph S. Gu, Qing |
| author_facet | Li, Xi Biswas, Disha Zhou, Peng Brigner, Wesley H. Capuano, Anna Friedman, Joseph S. Gu, Qing |
| contents | While software implementations of neural networks have driven significant advances in computation, the von Neumann architecture imposes fundamental limitations on speed and energy efficiency. Neuromorphic networks, with structures inspired by the brain's architecture, offer a compelling solution with the potential to approach the extreme energy efficiency of neurobiological systems. Photonic neuromorphic networks (PNNs) are particularly attractive because they leverage the inherent advantages of light, namely high parallelism, low latency, and exceptional energy efficiency. Previous PNN demonstrations have largely focused on device-level functionalities or system-level implementations reliant on supervised learning and inefficient optical-electrical-optical (OEO) conversions. Here, we introduce a purely photonic deep PNN architecture that enables online, unsupervised learning. We propose a local feedback mechanism operating entirely in the optical domain that implements a Hebbian learning rule using non-volatile phase-change material synapses. We experimentally demonstrate this approach on a non-trivial letter recognition task using a commercially available fiber-optic platform and achieve a 100 percent recognition rate, showcasing an all-optical solution for efficient, real-time information processing. This work unlocks the potential of photonic computing for complex artificial intelligence applications by enabling direct, high-throughput processing of optical information without intermediate OEO signal conversions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22300 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Online unsupervised Hebbian learning in deep photonic neuromorphic networks Li, Xi Biswas, Disha Zhou, Peng Brigner, Wesley H. Capuano, Anna Friedman, Joseph S. Gu, Qing Optics Disordered Systems and Neural Networks Emerging Technologies Machine Learning While software implementations of neural networks have driven significant advances in computation, the von Neumann architecture imposes fundamental limitations on speed and energy efficiency. Neuromorphic networks, with structures inspired by the brain's architecture, offer a compelling solution with the potential to approach the extreme energy efficiency of neurobiological systems. Photonic neuromorphic networks (PNNs) are particularly attractive because they leverage the inherent advantages of light, namely high parallelism, low latency, and exceptional energy efficiency. Previous PNN demonstrations have largely focused on device-level functionalities or system-level implementations reliant on supervised learning and inefficient optical-electrical-optical (OEO) conversions. Here, we introduce a purely photonic deep PNN architecture that enables online, unsupervised learning. We propose a local feedback mechanism operating entirely in the optical domain that implements a Hebbian learning rule using non-volatile phase-change material synapses. We experimentally demonstrate this approach on a non-trivial letter recognition task using a commercially available fiber-optic platform and achieve a 100 percent recognition rate, showcasing an all-optical solution for efficient, real-time information processing. This work unlocks the potential of photonic computing for complex artificial intelligence applications by enabling direct, high-throughput processing of optical information without intermediate OEO signal conversions. |
| title | Online unsupervised Hebbian learning in deep photonic neuromorphic networks |
| topic | Optics Disordered Systems and Neural Networks Emerging Technologies Machine Learning |
| url | https://arxiv.org/abs/2601.22300 |