Efficient optical reservoir computing for parallel data processing

We propose and experimentally demonstrate an optical reservoir computing system in free space, using second-harmonic generation for nonlinear kernel functions and a scattering medium to enhance reservoir nodes interconnection. We test it for one-step and multi-step predication of Mackey-Glass time series with different input-mapping methods on a spatial light modulator. For one-step prediction, we achieve 1.8 x 10(-3) normalized mean squared error (NMSE). For the multi-step prediction, we explore two different mapping methods: linear-combination and concatenation, achieving 16-step prediction with NMSE as low as 3.5 x 10(-4). Robust and superior for multi-step prediction, our approach and design have potential for parallel data processing tasks such as video prediction, speech translation, and so on. (C) 2022 Optica Publishing Group

Automated summary

We propose and experimentally demonstrate an optical reservoir computing system in free space, using second-harmonic generation for nonlinear kernel functions and a scattering medium to enhance reservoir nodes interconnection. Through experiments on Mackey-Glass time series, we validate the performance of the system in one-step and multi-step prediction. The results show that the system exhibits robust and superior performance in multi-step prediction and has potential for applications in parallel data processing tasks such as video prediction and speech translation.