Loading...

Virtual reservoir computer using an optical resonator

Boshgazi, S ; Sharif University of Technology | 2022

50 Viewed
  1. Type of Document: Article
  2. DOI: 10.1364/OME.450256
  3. Publisher: The Optical Society , 2022
  4. Abstract:
  5. Reservoir computing is a machine learning approach that enables us to use recurrent neural networks without involving the complexity of training algorithms and make hardware implementation possible. We present a novel photonic architecture of a reservoir computer that employs a nonlinear node and a resonator to implement a virtual recurrent neural network. This resonator behaves as an echo generator component that substitutes the delay line in delaybased reservoir computers available in the literature. The virtual neural network formed in our implementation is fundamentally different from the delay-based reservoir computers. Different virtual architectures based on the FSR and the Finesse of the resonator are investigated to provide higher performance depending on the task. We test the performance of our proposed reservoir by 3 benchmark tasks, signal classification, nonlinear channel equalization, and memory capacity. Our system enhances the memory capacity of the reservoir compared to the delay-based systems and shows reliable results in signal classification and nonlinear channel equalization. © 2022 Optica Publishing Group
  6. Keywords:
  7. Benchmarking ; Computational complexity ; Equalizers ; Memory architecture ; Network architecture ; Resonators ; Hardware implementations ; Machine learning approaches ; Memory capacity ; Neural-networks ; Nonlinear channels equalization ; Performance ; Reservoir Computing ; Signal classification ; Training algorithms ; Virtual architecture ; Recurrent neural networks
  8. Source: Optical Materials Express ; Volume 12, Issue 3 , 2022 , Pages 1140-1153 ; 21593930 (ISSN)
  9. URL: https://opg.optica.org/ome/fulltext.cfm?uri=ome-12-3-1140&id=469606