تقرير
Optical next generation reservoir computing
| العنوان: | Optical next generation reservoir computing |
|---|---|
| المؤلفون: | Wang, Hao, Hu, Jianqi, Baek, YoonSeok, Tsuchiyama, Kohei, Joly, Malo, Liu, Qiang, Gigan, Sylvain |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science Nonlinear Sciences Physics (Other) |
| مصطلحات موضوعية: | Physics - Optics, Computer Science - Emerging Technologies, Nonlinear Sciences - Chaotic Dynamics |
| الوصف: | Artificial neural networks with internal dynamics exhibit remarkable capability in processing information. Reservoir computing (RC) is a canonical example that features rich computing expressivity and compatibility with physical implementations for enhanced efficiency. Recently, a new RC paradigm known as next generation reservoir computing (NGRC) further improves expressivity but compromises its physical openness, posing challenges for neuromorphic realizations. Here we demonstrate optical NGRC with large-scale computations performed by light scattering through disordered media. In contrast to conventional optical RC implementations, we drive our optical reservoir directly with time-delayed inputs. Much like digital NGRC that relies on polynomial features of delayed inputs, our optical reservoir also implicitly generates these polynomial features for desired functionalities. By leveraging the domain knowledge of the reservoir inputs, we show that the optical NGRC not only predicts the short-term dynamics of the low-dimensional Lorenz63 and large-scale Kuramoto-Sivashinsky chaotic time series, but also replicates their long-term ergodic properties. Optical NGRC shows superiority in shorter training length, increased interpretability and fewer hyperparameters compared to conventional optical RC, while achieving state-of-the-art forecasting performance. Given its scalability and versatility, our optical NGRC framework also paves the way for other next generation physical reservoirs, new applications and architectures in a broad sense. |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2404.07857 |
| رقم الأكسشن: | edsarx.2404.07857 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |