论文信息 - Autonomous bio-inspired photonic processor based on reservoir computing paradigm

Autonomous bio-inspired photonic processor based on reservoir computing paradigm

We study numerically a realistic model of a high-performance power efficient photonic neural network coupled to an analog electronic readout layer in order to demonstrate its potential for high-speed computing with no need for external digital post-processing.

Marc Haelterman | Serge Massar | Anteo Smerieri | Quentin Vinckier | Francois Duport

[1] Daniel Brunner,et al. Parallel photonic information processing at gigabyte per second data rates using transient states , 2013, Nature Communications.

[2] Benjamin Schrauwen,et al. Analog readout for optical reservoir computers , 2012, NIPS.

[3] Benjamin Schrauwen,et al. Reservoir Computing Trends , 2012, KI - Künstliche Intelligenz.

[4] L. Appeltant,et al. Information processing using a single dynamical node as complex system , 2011, Nature communications.

[5] Geert Morthier,et al. Experimental demonstration of reservoir computing on a silicon photonics chip , 2014, Nature Communications.

[6] Benjamin Schrauwen,et al. Optoelectronic Reservoir Computing , 2011, Scientific Reports.

[7] Serge Massar,et al. High performance photonic reservoir computer based on a coherently driven passive cavity , 2015, ArXiv.