# Deep photonic reservoir computing recurrent network

arXiv: https://arxiv.org/abs/2309.05246 · HTML: https://mlsanity.com/paper/2309.05246/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2023.

## Built on by (most cited first, 2 of 2)

- [Beyond Terabit/s Integrated Neuromorphic Photonic Processor for DSP-Free Optical Interconnects](https://mlsanity.com/paper/2504.15044/) (2025)
- [Information Processing Capacity of Stationary Physical Systems: Theory, Data-efficient Estimation Methods, and Photonic Demonstration](https://mlsanity.com/paper/2605.19152/) (2026)

## Abstract (arXiv)

Deep neural networks usually process information through multiple hidden layers. However, most hardware reservoir computing recurrent networks only have one hidden reservoir layer, which significantly limits the capability of solving real-world complex tasks. Here we show a deep photonic reservoir computing (PRC) architecture, which is constructed by cascading injection-locked semiconductor lasers. In particular, the connection between successive hidden layers is all optical, without any optical-electrical conversion or analog-digital conversion. The proof of concept is demonstrated on a PRC consisting of 4 hidden layers and 320 interconnected neurons. In addition, we apply the deep PRC in the real-world signal equalization of an optical fiber communication system. It is found that the deep PRC owns strong ability to compensate the nonlinearity of fibers.