English

Wavelength-multiplexed Delayed Inputs for Memory Enhancement of Microring-based Reservoir Computing

Neural and Evolutionary Computing 2023-12-08 v1 Emerging Technologies Machine Learning

Abstract

We numerically demonstrate a silicon add-drop microring-based reservoir computing scheme that combines parallel delayed inputs and wavelength division multiplexing. The scheme solves memory-demanding tasks like time-series prediction with good performance without requiring external optical feedback.

Keywords

Cite

@article{arxiv.2312.04204,
  title  = {Wavelength-multiplexed Delayed Inputs for Memory Enhancement of Microring-based Reservoir Computing},
  author = {Bernard J. Giron Castro and Christophe Peucheret and Francesco Da Ros},
  journal= {arXiv preprint arXiv:2312.04204},
  year   = {2023}
}

Comments

2 pages, 2 figures. Submitted to Conference on Lasers and Electro-Optics (CLEO) 2024

R2 v1 2026-06-28T13:43:51.127Z