Demonstration of Reservoir Computing Using Optoelectronic Oscillators With Direct Laser Modulation

We demonstrate the first experimental investigation on the performance of simplified optoelectronic oscillator (OEO) reservoir computers (RCs) operating on the standard Santa Fe task, comparing our results against numerical simulations. “Simplifying” the OEO by removing the Mach-Zehnder modulator (MZM) and directly modulating the laser diode with the injected signal is an important step towards operationalizing OEO-based reservoir computing (OEO-RC), as this helps pave the way to chip-scale optical reservoir computers where all the components of the reservoir layer can be included in a single fabricated photonic circuit. Our results show that a simplified OEO-RC can meet or exceed the performance of more computationally complex OEO-RC and similar delayed all-photonic RC on benchmark tests, likely indicating suitability for the architecture to process real-world, complex data.

Authors

Institutions

Publication Details

Journal
IEEE Photonics Technology Letters
Published
2024-10-09
DOI
https://doi.org/10.1109/lpt.2024.3477352
Citations
3
Primary Topic
Neural Networks and Reservoir Computing
Type
article
Field-Weighted Citation Impact
1.04
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Demonstration of Reservoir Computing Using Optoelectronic Oscillators With Direct Laser Modulation

Yanne K. Chembo, Benjamin H. Klimko
3 citations
IEEE Photonics Technology Letters
Neural Networks and Reservoir Computing
1.04
article

Demonstration of Reservoir Computing Using Optoelectronic Oscillators With Direct Laser Modulation

Yanne K. Chembo, Benjamin H. Klimko
article en
3 citations

Abstract

We demonstrate the first experimental investigation on the performance of simplified optoelectronic oscillator (OEO) reservoir computers (RCs) operating on the standard Santa Fe task, comparing our results against numerical simulations. “Simplifying” the OEO by removing the Mach-Zehnder modulator (MZM) and directly modulating the laser diode with the injected signal is an important step towards operationalizing OEO-based reservoir computing (OEO-RC), as this helps pave the way to chip-scale optical reservoir computers where all the components of the reservoir layer can be included in a single fabricated photonic circuit. Our results show that a simplified OEO-RC can meet or exceed the performance of more computationally complex OEO-RC and similar delayed all-photonic RC on benchmark tests, likely indicating suitability for the architecture to process real-world, complex data.

IEEE Photonics Technology LettersVol. 36(23)
University of Maryland, College Park (US)
Affordable and clean energy
Openalex Percentile: Top 19%
Neural Networks and Reservoir Computing
1.04
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Demonstration of Reservoir Computing Using Optoelectronic Oscillators With Direct Laser Modulation — Yanne K. Chembo, Benjamin H. Klimko · IEEE Photonics Technology Letters (2024) | TGRS Research Map | TGRS