Improving Time Series Recognition and Prediction with Networks and Ensembles of Passive Photonic Reservoirs
Loading...
Date
2019
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE Journal of Selected Topics in Quantum Electronics
Abstract
As the performance increase of traditional Von-
Neumann computing attenuates, new approaches to computing
need to be found. A promising approach for low-power computing
at high bitrates is integrated photonic reservoir computing. In the
past though, the feasible reservoir size and computational power
of integrated photonic reservoirs have been limited by hardware
constraints. An alternative solution to building larger reservoirs is
the combination of several small reservoirs to match or exceed the
performance of a single bigger one. This work summarizes our
efforts to increase the available computational power by combining
multiple reservoirs into a single computing architecture. We
investigate several possible combination techniques and evaluate
their performance using the classic XOR and header recognition
tasks as well as the well-known Santa Fe chaotic laser prediction
task. Our findings suggest that a new paradigm of feeding a
reservoir’s output into the readout structure of the next one
shows consistently good results for various tasks as well as for
both electrical and optical readouts and coupling schemes.
Description
Keywords
integrated photonic reservoir computing, deep reservoir computing, Scalable reservoir computing, Unconventional computing, Neuro-inspired computing, Neuromorphic computing.
Citation
Freiberger, M., Sackesyn, S., Ma, C., Katumba, A., Bienstman, P., & Dambre, J. (2019). Improving time series recognition and prediction with networks and ensembles of passive photonic reservoirs. IEEE Journal of Selected Topics in Quantum Electronics, 26(1), 1-11.