Photonic reservoir computing with complex networks

Abstract

Photonic reservoir computing has attracted increasing attention as a fast and low-cost approach for time-series prediction. Photonic reservoir computing utilizes the high speed, broad bandwidth, and spatial parallelism of light. However, the effect of the internal connection structure (network topology) on the computing performance has not been investigated for large-scale photonic reservoirs. In this study, we experimentally and numerically demonstrate photonic reservoir computing using a spatial light modulator to systematically evaluate the relationship between the network topology and the performance of reservoir computing. We introduce complex network structures such as small-world and scale-free network topologies of the internal nodes in the reservoir. We perform the memory capacity measurement and the one-step-ahead prediction task of the chaotic time series to compare the performance. We found that the small-world network exhibits the maximum memory capacity and the best prediction performance. Our numerical calculations reveal that the performance of the time-series prediction can be optimized by changing the rewiring probability of the network and the leak rate of the reservoir. We also implement photonic human brain network as a reservoir, which is designed by the connectomes of human brain activities. We found that the network topology strongly affects the performance of reservoir computing, and the small-world network structure outperforms the other configurations.

Nonlinear pluggable optics: Digital signal processing-free Intensity Modulated Direct Detection links using analog photonic Next Generation Reservoir Computing
Nicholas Cox, Joseph Murray, Ross Schermer +6
Optics Express16 Oct 2026Peer-reviewedLicence not statedOptics & photonicsCrossref
Frequency-Multiplexed Photonic Reservoir Computing with a Synchronously Pulse-Driven Optical Cavity
Amir Arsalan Arabieh, Simon-Pierre Gorza, Serge Massar
arXiv10 Sep 2026PreprintarXiv licenceFull textOptics & photonicsarXiv
Photonic reservoir computing with dimensionally compressed readout
Gerald Kobi, Mohab Abdalla, Miguel C. Soriano +1
arXiv7 Sep 2026PreprintarXiv licenceFull textOptics & photonicsarXiv
When Does Interference Help Learning? Kernel Geometry as a Pre-Experimental Test for Photonic Reservoir Computing
Oishik Kar, Aswath Babu H
arXiv12 Oct 2026PreprintCC0Full textQuantum physics & quantum informationarXiv
Reservoir computing generalized: Exploiting complex dynamics via time-invariant transformation
Tomoyuki Kubota, Sumito Tsunegi, Kohei Nakajima
Physical Review Research1 Nov 2026Peer-reviewedPublisher termsAtomic, molecular & optical physicsCrossref

Cite

BibTeX RIS

BibTeX

@misc{park2026photonic,
  title = {{Photonic reservoir computing with complex networks}},
  author = {Sion Park and Kohei Watabe and Satoshi Sunada and Tomoki Yamagami and Atsushi Uchida},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2607.23285},
  eprint = {2607.23285},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.23285},
}

RIS

TY  - UNPB
TI  - Photonic reservoir computing with complex networks
AU  - Sion Park
AU  - Kohei Watabe
AU  - Satoshi Sunada
AU  - Tomoki Yamagami
AU  - Atsushi Uchida
PY  - 2026
DA  - 2026/10/13
PB  - arXiv
DO  - 10.48550/arxiv.2607.23285
UR  - https://arxiv.org/abs/2607.23285
AB  - Photonic reservoir computing has attracted increasing attention as a fast and low-cost approach for time-series prediction. Photonic reservoir computing utilizes the high speed, broad bandwidth, and spatial parallelism of light. However, the effect of the internal connection structure (network topology) on the computing performance has not been investigated for large-scale photonic reservoirs. In this study, we experimentally and numerically demonstrate photonic reservoir computing using a spatial light modulator to systematically evaluate the relationship between the network topology and the performance of reservoir computing. We introduce complex network structures such as small-world and scale-free network topologies of the internal nodes in the reservoir. We perform the memory capacity measurement and the one-step-ahead prediction task of the chaotic time series to compare the performance. We found that the small-world network exhibits the maximum memory capacity and the best prediction performance. Our numerical calculations reveal that the performance of the time-series prediction can be optimized by changing the rewiring probability of the network and the leak rate of the reservoir. We also implement photonic human brain network as a reservoir, which is designed by the connectomes of human brain activities. We found that the network topology strongly affects the performance of reservoir computing, and the small-world network structure outperforms the other configurations.
ER  -

Abstract

Related

Cite