Brain-inspired photonic signal processor for periodic pattern generation and chaotic system emulation

Reservoir computing is a bio-inspired computing paradigm for processing time-dependent signals. Its hardware implementations have received much attention because of their simplicity and remarkable performance on a series of benchmark tasks. In previous experiments the output was uncoupled from the system and in most cases simply computed offline on a post-processing computer. However, numerical investigations have shown that feeding the output back into the reservoir would open the possibility of long-horizon time series forecasting. Here we present a photonic reservoir computer with output feedback, and demonstrate its capacity to generate periodic time series and to emulate chaotic systems. We study in detail the effect of experimental noise on system performance. In the case of chaotic systems, this leads us to introduce several metrics, based on standard signal processing techniques, to evaluate the quality of the emulation. Our work significantly enlarges the range of tasks that can be solved by hardware reservoir computers, and therefore the range of applications they could potentially tackle. It also raises novel questions in nonlinear dynamics and chaos theory.

[1]  Laurent Larger,et al.  Photonic nonlinear transient computing with multiple-delay wavelength dynamics. , 2012, Physical review letters.

[2]  Michiel Hermans,et al.  Towards pattern generation and chaotic series prediction with photonic reservoir computers , 2016, SPIE LASE.

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

[4]  Peter Tiño,et al.  Minimum Complexity Echo State Network , 2011, IEEE Transactions on Neural Networks.

[5]  Benjamin Schrauwen,et al.  Locomotion Without a Brain: Physical Reservoir Computing in Tensegrity Structures , 2013, Artificial Life.

[6]  Marc Haelterman,et al.  Autonomous all-photonic processor based on reservoir computing paradigm , 2016, 2016 Conference on Lasers and Electro-Optics (CLEO).

[7]  L. Glass,et al.  Oscillation and chaos in physiological control systems. , 1977, Science.

[8]  Benjamin Schrauwen,et al.  Frequency modulation of large oscillatory neural networks , 2014, Biological Cybernetics.

[9]  Gordon Pipa,et al.  Persistent Memory in Single Node Delay-Coupled Reservoir Computing , 2016, PloS one.

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

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

[12]  Benjamin Schrauwen,et al.  Phoneme Recognition with Large Hierarchical Reservoirs , 2010, NIPS.

[13]  Volnei A. Pedroni.  Circuit Design with VHDL , 2004 .

[14]  Herbert Jaeger,et al.  Echo state network , 2007, Scholarpedia.

[15]  Jochen J. Steil,et al.  Regularization and stability in reservoir networks with output feedback , 2012, Neurocomputing.

[16]  Min Han,et al.  L1/2 Norm Regularized Echo State Network for Chaotic Time Series Prediction , 2016, ICONIP.

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

[18]  Tadashi Yamazaki,et al.  The cerebellum as a liquid state machine , 2007, Neural Networks.

[19]  J. D. Farmer,et al.  Chaotic attractors of an infinite-dimensional dynamical system , 1982 .

[20]  Michiel Hermans,et al.  Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalization , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[21]  Michiel Hermans,et al.  Towards Adjustable Signal Generation with Photonic Reservoir Computers , 2016, ICANN.

[22]  Benjamin Schrauwen,et al.  A comparative study of Reservoir Computing strategies for monthly time series prediction , 2010, Neurocomputing.

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

[24]  Herbert Jaeger,et al.  Controlling Recurrent Neural Networks by Conceptors , 2014, ArXiv.

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

[26]  Guoqiang Peter Zhang,et al.  Neural Networks for Time-Series Forecasting , 2012, Handbook of Natural Computing.

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

[28]  Serge Massar,et al.  Fully analogue photonic reservoir computer , 2016, Scientific Reports.

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

[30]  Paul Horowitz,et al.  The Art of Electronics , 1980 .

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

[32]  Herbert Jaeger,et al.  Conceptors: an easy introduction , 2014, ArXiv.

[33]  Serge Massar,et al.  Online Training for High-Performance Analogue Readout Layers in Photonic Reservoir Computers , 2017, Cognitive Computation.

[34]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[35]  Serge Massar,et al.  All-optical Reservoir Computing , 2012, Optics express.

[36]  Benjamin Schrauwen,et al.  Stable Output Feedback in Reservoir Computing Using Ridge Regression , 2008, ICANN.

[37]  John Porrill,et al.  At the Edge of Chaos: How Cerebellar Granular Layer Network Dynamics Can Provide the Basis for Temporal Filters , 2015, PLoS Comput. Biol..

[38]  Daniela Fischer.  Differential Equations Dynamical Systems And An Introduction To Chaos , 2016 .

[39]  L. F. Abbott,et al.  Generating Coherent Patterns of Activity from Chaotic Neural Networks , 2009, Neuron.

[40]  E. Lorenz.  Deterministic nonperiodic flow , 1963 .

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

[42]  Elaine B. Barker,et al.  A Statistical Test Suite for Random and Pseudorandom Number Generators for Cryptographic Applications , 2000 .