Online training of an optoelectronic reservoir computer

Reservoir Computing is a bio-inspired computing paradigm for processing time dependent signals. Its analog implementations equal and sometimes outperform other digital algorithms on a series of benchmark tasks. Their performance can be increased by switching from offline to online training method. Here we present the first online trained opto-electronic reservoir computer. The system is tested on a channel equalisation task and the algorithm is executed by an FPGA chip. We report performances close to previous implementations and demonstrate the benefits of online training on a non-stationary task that could not be easily solved using offline methods.

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

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

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

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

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

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

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

[8]  Benjamin Schrauwen,et al.  Compact hardware liquid state machines on FPGA for real-time speech recognition , 2008, Neural Networks.

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

[10]  Junghsi Lee,et al.  Adaptive algorithms for bilinear filtering , 1994, Optics & Photonics.

[11]  G. Arfken.  Mathematical Methods for Physicists , 1967 .

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

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

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

[15]  Jochen J. Steil,et al.  Recent advances in efficient learning of recurrent networks , 2009, ESANN.

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

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

[18]  Miguel C. Soriano,et al.  Reservoir computing with a single time-delay autonomous Boolean node , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[19]  Serge Massar,et al.  FPGA Implementation of Reservoir Computing with Online Learning , 2015 .

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