Reservoir Computing Using Laser Networks

Reservoir computing is a neuromorphic computing scheme inspired by the human brain. It has found great success as a versatile hardware-compatible application of machine learning concepts. In this paper, we highlight the fundamental working principles and important characteristics of reservoir computing with a particular focus on photonic systems and networks. These systems can further be enhanced by the inclusion of delayed variables to produce complex spatiotemporally mixed “time-multiplexed” networks. We use a simple nonlinear oscillator model, that is not only applicable to lasers, but can also describe a variety of other oscillating systems.

[1]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

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

[3]  Peter Tiño,et al.  Simple Deterministically Constructed Cycle Reservoirs with Regular Jumps , 2012, Neural Computation.

[4]  Benjamin Schrauwen,et al.  Information Processing Capacity of Dynamical Systems , 2012, Scientific Reports.

[5]  Miguel C. Soriano,et al.  Photonic delay systems as machine learning implementations , 2015, J. Mach. Learn. Res..

[6]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[7]  Benjamin Schrauwen,et al.  Toward optical signal processing using photonic reservoir computing. , 2008, Optics express.

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

[9]  A. S. Weigend,et al.  Results of the time series prediction competition at the Santa Fe Institute , 1993, IEEE International Conference on Neural Networks.

[10]  Laurent Larger,et al.  Tutorial: Photonic Neural Networks in Delay Systems , 2018, Journal of Applied Physics.

[11]  M. C. Soriano,et al.  Advances in photonic reservoir computing , 2017 .

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

[13]  Atsushi Uchida,et al.  Impact of input mask signals on delay-based photonic reservoir computing with semiconductor lasers. , 2018, Optics express.

[14]  André Röhm,et al.  Multiplexed networks: reservoir computing with virtual and real nodes , 2018, Journal of Physics Communications.

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

[16]  Luis Pesquera,et al.  Reservoir Computing with an Ensemble of Time-Delay Reservoirs , 2017, Cognitive Computation.

[17]  D Syvridis,et al.  Experimental synchrony of semiconductor lasers in coupled networks. , 2016, Optics express.

[18]  R. Lang,et al.  External optical feedback effects on semiconductor injection laser properties , 1980 .

[19]  Atsushi Uchida,et al.  Laser dynamical reservoir computing with consistency: an approach of a chaos mask signal. , 2016, Optics express.

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

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

[22]  Benjamin Schrauwen,et al.  Parallel Reservoir Computing Using Optical Amplifiers , 2011, IEEE Transactions on Neural Networks.

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

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

[25]  Jaideep Pathak,et al.  Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data. , 2017, Chaos.

[26]  Amir F. Atiya,et al.  New results on recurrent network training: unifying the algorithms and accelerating convergence , 2000, IEEE Trans. Neural Networks Learn. Syst..

[27]  Conrad Sanderson,et al.  Armadillo: a template-based C++ library for linear algebra , 2016, J. Open Source Softw..

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