Open AccessReducing the phase sensitivity of laser-based optical reservoir computing systems
Author(s) -
Romain Modeste Nguimdo,
Guy Verschaffelt,
Jan Danckaert,
Guy Van der Sande
Publication year - 2016
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.24.001238
Subject(s) - reservoir computing , computer science , sensitivity (control systems) , signal (programming language) , laser , process (computing) , signal processing , reduction (mathematics) , optics , phase (matter) , electronic engineering , computer hardware , physics , digital signal processing , engineering , geometry , mathematics , quantum mechanics , machine learning , recurrent neural network , artificial neural network , programming language , operating system
Optical implementations of reservoir computing systems are very promising because of their high processing speeds and the possibility to process several tasks in parallel. These systems can be implemented using semiconductor lasers subject to optical delayed feedback and optical injection. While the amount of the feedback/injection can be easily controlled, it is much more difficult to control the optical feedback/injection phase. We present extensive numerical investigations of the influence of the feedback/injection phases on laser-based reservoir computing systems with feedback. We show that a change in the phase can lead to a strong reduction in the reservoir computing system performance. We introduce a new readout layer design that -at least for some tasks- reduces this sensitivity to changes in the phase. It consists in optimizing the readout weights from a coherent combination of the reservoir's readout signal and its delayed version rather than only from the reservoir's readout signal as is usually done.