Reinforcement Learning in a Large Scale Photonic Network

In recent years Neural Networks or Neuromorphic Computing has significantly shifted the limits of what is computationally possible [1]. Recurrent Neural Networks are nonlinear dynamical systems, and as such they are inherently capable to process temporal information or signals. They show excellent performance in the prediction of chaotic trajectories or in the equalization of nonlinearly corrupted communication channels [2].

[1]  Laurent Larger,et al.  High-Speed Photonic Reservoir Computing Using a Time-Delay-Based Architecture: Million Words per Second Classification , 2017 .

[2]  S. Mikkat,et al.  The Regulatory Small RNA MarS Supports Virulence of Streptococcus pyogenes , 2017, Scientific Reports.

[3]  Daniel Brunner,et al.  Conditions for reservoir computing performance using semiconductor lasers with delayed optical feedback. , 2017, Optics express.

[4]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[5]  Geoffrey E. Hinton,et al.  Transforming Auto-Encoders , 2011, ICANN.

[6]  Ellen Zhou,et al.  Neuromorphic photonic networks using silicon photonic weight banks , 2017, Scientific Reports.

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

[8]  J. Goodman.  Introduction to Fourier optics , 1969 .

[9]  Serge Massar,et al.  Brain-Inspired Photonic Signal Processor for Generating Periodic Patterns and Emulating Chaotic Systems , 2017 .

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

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

[12]  Ingo Fischer,et al.  Photonic machine learning implementation for signal recovery in optical communications , 2018, Scientific Reports.

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

[14]  Bhavin J. Shastri,et al.  Neuromorphic photonic networks using silicon photonic weight banks , 2016, Scientific Reports.

[15]  Dirk Englund,et al.  Deep learning with coherent nanophotonic circuits , 2017, 2017 Fifth Berkeley Symposium on Energy Efficient Electronic Systems & Steep Transistors Workshop (E3S).

[16]  Theo Lasser,et al.  Fast focus field calculations. , 2006, Optics express.

[17]  Laurent Larger,et al.  Reinforcement Learning in a large scale photonic Recurrent Neural Network , 2017, Optica.

[18]  Ingo Fischer,et al.  Reconfigurable semiconductor laser networks based on diffractive coupling. , 2015, Optics letters.

[19]  M. Eremets,et al.  Ammonia as a case study for the spontaneous ionization of a simple hydrogen-bonded compound , 2014, Nature Communications.

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

[21]  L Pesquera,et al.  Photonic information processing beyond Turing: an optoelectronic implementation of reservoir computing. , 2012, Optics express.