Abstract
Reservoir computing architectures offer important benefits for the implementation of a neural network in a physical medium, as the weighted interconnections between the internal nodes are random and fixed. Experimental results on a time-delay photonic reservoir computer based on directly modulated Vertical Cavity Surface Emitting Lasers and multi-mode fiber couplers are presented. The neuron is made of photodiode, non-linear amplifier and laser chips. The NARMA10 chaotic time-series task is performed with a configuration having 25 virtual nodes operating at 1 GS/s. Experimental and simulated error ranges are in good agreement, which is promising for an expansion to a more elaborate system. The potential of this scheme for the realization of a photonic reservoir cluster device operating at very high speed with low power and a small footprint with a large number of interacting physical and virtual neurons is discussed.
Supported by the New Energy Development Organization (NEDO). P.A. acknowledges financial support by the founders of the Chaire Photonique.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Tanaka, G., et al.: Recent advances in physical reservoir computing: a review. Neural Netw. 115, 100–123 (2019)
Appeltant, L., et al.: Information processing using a single dynamical node as complex system. Nat. Comm. 2, 468 (2011)
Héroux, J.B., et al.: Energy-efficient 1060-nm optical link operating up to 28 Gb/s. J. Lightwave Technol. 33, 733–740 (2015)
Héroux, J.B., Kanazawa, N., Nakano, D.: Delayed feedback reservoir computing with VCSEL. In: Cheng, L., Leung, A.C.S., Ozawa, S. (eds.) ICONIP 2018. LNCS, vol. 11301, pp. 594–602. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-04167-0_54
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Héroux, J.B., Kanazawa, N., Antonik, P. (2019). Time Series Processing with VCSEL-Based Reservoir Computer. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions. ICANN 2019. Lecture Notes in Computer Science(), vol 11731. Springer, Cham. https://doi.org/10.1007/978-3-030-30493-5_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-30493-5_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30492-8
Online ISBN: 978-3-030-30493-5
eBook Packages: Computer ScienceComputer Science (R0)