Computing using delayed feedback systems: towards photonics

Reservoir computing has recently been introduced as a new paradigm in the eld of machine learning. It is based on the dynamical properties of a network of randomly connected nodes or neurons and shows to be very promising to solve complex classication problems in a computationally ecient way. The key idea is that an input generates nonlinearly transient behavior rendering transient reservoir states suitable for linear classication. Our goal is to study up to which extent systems with delay, and especially photonic systems, can be used as reservoirs. Recently an new architecture has been proposed1 , based on a single nonlinear node with delayed feedback. An electronic1 and an opto-electronic implementation2, 3 have been demonstrated and both have proven to be very successful in terms of performance. This simple conguration, which replaces an entire network of randomly connected nonlinear nodes with one single hardware node and a delay line, is signicantly easier to implement experimentally. It is no longer necessary to construct an entire network of hundreds or even thousands of circuits, each one representing a node. With this approach one node and a delay line suce to construct a computational unit. In this manuscript, we present a further investigation of the properties of delayed feedback congurations used as a reservoir. Instead of quantifying the performance as an error obtained for a certain benchmark, we now investigate a task-independent property, the linear memory of the system.

[1]  V Flunkert,et al.  Mismatch and synchronization: influence of asymmetries in systems of two delay-coupled lasers. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[2]  J. Danckaert,et al.  Exploring multistability in semiconductor ring lasers: theory and experiment. , 2009, Physical review letters.

[3]  Danko Nikolic,et al.  Temporal dynamics of information content carried by neurons in the primary visual cortex , 2006, NIPS.

[4]  J. Danckaert,et al.  Solitary and coupled semiconductor ring lasers as optical spiking neurons. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

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

[6]  I Fischer,et al.  Role of delay for the symmetry in the dynamics of networks. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[7]  M. C. Soriano,et al.  Dynamics, correlation scaling, and synchronization behavior in rings of delay-coupled oscillators. , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.

[8]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[9]  Bob Nagler,et al.  Frequency response of polarization switching in vertical-cavity surface-emitting lasers , 2003 .

[10]  Michael J. Strain,et al.  Semiconductor snail lasers , 2010 .

[11]  J. Danckaert,et al.  Topological insight into the non-arrhenius mode hopping of semiconductor ring lasers. , 2008, Physical review letters.

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

[13]  Jan Danckaert,et al.  Rate equations for vertical-cavity surface-emitting lasers , 2003 .

[14]  Siyuan Yu,et al.  Integrated Small-Sized Semiconductor Ring Laser With Novel Retro-Reflector Cavity , 2008, IEEE Photonics Technology Letters.

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

[16]  I Fischer,et al.  Amplitude and phase effects on the synchronization of delay-coupled oscillators. , 2010, Chaos.

[17]  Kestutis Pyragas,et al.  An electronic analog of the Mackey-Glass system , 1995 .

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

[19]  Marc Sorel,et al.  Excitability in optical systems close to Z2-symmetry , 2010, 1108.3738.

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

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

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

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

[24]  Johannes Schemmel,et al.  Edge of Chaos Computation in Mixed-Mode VLSI - A Hard Liquid , 2004, NIPS.

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

[26]  M. C. Soriano,et al.  Interplay of Current Noise and Delayed Optical Feedback on the Dynamics of Semiconductor Lasers , 2011, IEEE Journal of Quantum Electronics.