Open AccessImpact of input mask signals on delay-based photonic reservoir computing with semiconductor lasers
Author(s) -
Yoma Kuriki,
J. Nakayama,
Kiminori Takano,
Atsushi Uchida
Publication year - 2018
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.26.005777
Subject(s) - reservoir computing , noise (video) , signal (programming language) , photonics , semiconductor laser theory , optics , computer science , laser , amplitude , physics , acoustics , artificial intelligence , recurrent neural network , artificial neural network , image (mathematics) , programming language , machine learning
We experimentally investigate delay-based photonic reservoir computing using semiconductor lasers with optical feedback and injection. We apply different types of temporal mask signals, such as digital, chaos, and colored-noise mask signals, as the weights between the input signal and the virtual nodes in the reservoir. We evaluate the performance of reservoir computing by using a time-series prediction task for the different mask signals. The chaos mask signal shows superior performance than that of the digital mask signals. However, similar prediction errors can be achieved for the chaos and colored-noise mask signals. Mask signals with larger amplitudes result in better performance for all mask signals in the range of the amplitude accessible in our experiment. The performance of reservoir computing is strongly dependent on the cut-off frequency of the colored-noise mask signals, which is related to the resonance of the relaxation oscillation frequency of the laser used as the reservoir.