Abstract
Reservoir computing is a technique based on recurrent neural networks to process time-dependent signals [1]. Recently, we have successfully demonstrated, both experimentally and in simulation, a linear passive fiber cavity used as a hardware based reservoir computer [2]. On a wide range of benchmark tasks, this setup has better performances than the best digital algorithms and all previous experimental reservoir computers, see e.g. [3,4]. In the present work, we numerically investigate the use of an analog readout layer on this system, inspired by the one shown in [5]. The aim is to directly generate the output signal without any off-line post-processing. Our simulations include all the experimental limitations of the setup, e.g., device bandwidths, sampling rates, noise, resolutions, etc.
© 2015 IEEE
PDF ArticleMore Like This
Quentin Vinckier, François Duport, Marc Haelterman, and Serge Massar
FTu3B.6 Frontiers in Optics (FiO) 2015
Quentin Vinckier, Arno Bouwens, Marc Haelterman, and Serge Massar
SF1F.1 CLEO: Science and Innovations (CLEO:S&I) 2016
Peter Bienstman, Joni Dambre, Andrew Katumba, Matthias Freiberger, Floris Laporte, and Alessio Lugnan
M4F.4 Optical Fiber Communication Conference (OFC) 2018