Virtualization of a Photonic Reservoir Computer

Reservoir computer is an efficient dynamical computing concept that was introduced at the onset of this century for processing time-dependent signals. Several photonic implementations have demonstrated good performances, taking advantage of the components developed for optical telecommunications. However, in implementations based on a delay line that use an input desynchronized with respect to the period of the delay line, the effective used bandwidth is generally far from the one allowed by the physical setups. To use more of the available bandwidth, we propose an original solution that consists on time interleaving several reservoirs on the same physical setup. These are then used to process several tasks independently, but simultaneously on the same physical setup. We call them virtual reservoir computers. We report a proof-of-concept demonstration with three virtual reservoirs. The present results further demonstrate the versatility of photonic reservoir computing.

[1]  Romain Modeste Nguimdo,et al.  Simultaneous Computation of Two Independent Tasks Using Reservoir Computing Based on a Single Photonic Nonlinear Node With Optical Feedback , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Damien Rontani,et al.  All-Optical Reservoir Computing on a Photonic Chip Using Silicon-Based Ring Resonators , 2018, IEEE Journal of Selected Topics in Quantum Electronics.

[3]  Herbert Jaeger,et al.  Adaptive Nonlinear System Identification with Echo State Networks , 2002, NIPS.

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

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

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

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

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

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

[10]  M. C. Soriano,et al.  Information Processing Using Transient Dynamics of Semiconductor Lasers Subject to Delayed Feedback , 2013, IEEE Journal of Selected Topics in Quantum Electronics.

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

[12]  Chrisantha Fernando,et al.  Pattern Recognition in a Bucket , 2003, ECAL.

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

[14]  Jochen J. Steil,et al.  Memory in Backpropagation-Decorrelation O(N) Efficient Online Recurrent Learning , 2005, ICANN.

[15]  Benjamin Schrauwen,et al.  Isolated word recognition using a Liquid State Machine , 2005, ESANN.

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

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

[18]  Benjamin Schrauwen,et al.  An experimental unification of reservoir computing methods , 2007, Neural Networks.

[19]  Li Fang,et al.  All-optical reservoir computer based on saturation of absorption. , 2014, Optics express.

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

[21]  Benjamin Schrauwen,et al.  Reservoir Computing with Stochastic Bitstream Neurons , 2005 .

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

[23]  Ingo Fischer,et al.  High-Speed Optical Vector and Matrix Operations Using a Semiconductor Laser , 2013, IEEE Photonics Technology Letters.

[24]  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.

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

[26]  Marc Haelterman,et al.  Virtual Optical Reservoir Computing , 2014 .