1. Impact of optical coherence on the performance of large-scale spatiotemporal photonic reservoir computing systems
- Author
-
Romain Modeste Nguimdo, Piotr Antonik, Nicolas Marsal, Damien Rontani, Laboratoire Matériaux Optiques, Photonique et Systèmes (LMOPS), and CentraleSupélec-Université de Lorraine (UL)
- Subjects
Hardware_MEMORYSTRUCTURES ,Artificial neural network ,business.industry ,Computer science ,Reservoir computing ,Image processing ,02 engineering and technology ,021001 nanoscience & nanotechnology ,01 natural sciences ,Atomic and Molecular Physics, and Optics ,010309 optics ,Optics ,[NLIN.NLIN-PS]Nonlinear Sciences [physics]/Pattern Formation and Solitons [nlin.PS] ,0103 physical sciences ,Electronic engineering ,Photonics ,0210 nano-technology ,business ,Massively parallel ,Coherence (physics) - Abstract
International audience; Large-scale spatiotemporal photonic reservoir computer (RC) systems offer remarkable solutions for massively parallel processing of a wide variety of hard real-world tasks. In such systems, neural networks are created by either optical or electronic coupling. Here, we investigate the impact of the optical coherence on the performance of large-scale spatiotemporal photonic RCs by comparing a coherent (optical coupling between the reservoir nodes) and incoherent (digital coupling between the reservoir nodes) RC systems. Although the coherent configuration offers significant reduction on the computational load compared to the incoherent architecture, for image and video classification benchmark tasks, it is found that the incoherent RC configuration outperforms the coherent configuration. Moreover, the incoherent configuration is found to exhibit a larger memory capacity than the coherent scheme. Our results pave the way towards the optimization of implementation of large-scale RC systems.
- Published
- 2020
- Full Text
- View/download PDF