abstract
Reservoir computing is a neuromorphic architecture based on artificial neural networks. It has gathered significant attention due to its simplicity and efficiency in processing complex sequential data for real-world tasks. We propose an advanced optoelectronic reservoir computing system that uses a single nonlinear node comprised of a Mach-Zehnder interferometer, an optical delay line, and several high-bandwidth integrated optoelectronic components. This system shows efficient performance on benchmark tasks such as signal recognition with an accuracy of 100%, nonlinear channel equalization for generating reconstructed signals with symbol error rates of 10-55, and time-series predictions that reach normalized mean square errors in the order of 10- 2.
subject category
Optics; Physics
authors
Dias, LMS; Bastos, AR; Alves, T; Towe, E; Ferreira, RAS; André, PSB
our authors
Ana Rita da Naia Bastos
Researcher
Maria Rute de Amorim e Sá Ferreira André
Full professorProjects
Collaboratory for Emerging Technologies, CoLab (EMERGING TECHNOLOGIES)
Associated Laboratory CICECO-Aveiro Institute of Materials (LA/P/0006/2020)
acknowledgements
This work was developed within the scope of the project CICECO - Aveiro Institute of Materials, UID/50011/2025 & LA/P/0006/2020 (DOI 10.54499/LA/P/0006/2020) , financed by national funds through the FCT/MCTES (PIDDAC) and Instituto de Telecomunicaco es, UID/50008/2025 (10.54499/UID/50008/2025) , and LA/P/0109/2020 (DOI: 10.54499/LA/P/0109/2020) . LMSD thanks FCT for the PhD grant UI/BD/153491/2022, (DOI:10.54499/UI/BD/153491/2022) , financed by national funds through the FCT/MEC (PIDDAC) , and when appro-priate, cofinanced by FEDER under the PT2020 Partnership through European Regional Development Fund (ERDF) in the frame of Opera-tional Competitiveness and Internationalization Programme (POCI) . ARB acknowledges financial support by IT-Lisbon and FCT under Con-tract No. CEECINST/00058/2021/CP2816/CT0004 (DOI:10.54499/CEECINST/00058/2021/CP2816/CT0004) .