Analog readout for optical reservoir computers

Reservoir computing is a new, powerful and flexible machine learning technique that is easily implemented in hardware. Recently, by using a time-multiplexed architecture, hardware reservoir computers have reached performance comparable to digital implementations. Operating speeds allowing for real time information operation have been reached using optoelectronic systems. At present the main performance bottleneck is the readout layer which uses slow, digital postprocessing. We have designed an analog readout suitable for time-multiplexed optoelectronic reservoir computers, capable of working in real time. The readout has been built and tested experimentally on a standard benchmark task. Its performance is better than non-reservoir methods, with ample room for further improvement. The present work thereby overcomes one of the major limitations for the future development of hardware reservoir computers.

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

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

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

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

[5]  Benjamin Schrauwen,et al.  Reservoir computing: a photonic neural network for information processing , 2010, Photonics Europe.

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

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

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

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

[10]  Terrence J. Sejnowski,et al.  What Makes a Dynamical System Computationally Powerful , 2007 .

[11]  Herbert Jaeger,et al.  Optimization and applications of echo state networks with leaky- integrator neurons , 2007, Neural Networks.

[12]  Wolfgang Maass,et al.  A Reward-Modulated Hebbian Learning Rule Can Explain Experimentally Observed Network Reorganization in a Brain Control Task , 2010, The Journal of Neuroscience.

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

[14]  Benjamin Schrauwen,et al.  Memory versus non-linearity in reservoirs , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[15]  Thomas J. Naughton,et al.  Photonic neural networks , 2012, Nature Physics.

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

[17]  Benjamin Schrauwen,et al.  An overview of reservoir computing: theory, applications and implementations , 2007, ESANN.

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

[19]  W. Maass,et al.  What makes a dynamical system computationally powerful ? , 2022 .

[20]  Benjamin Schrauwen,et al.  Photonic reservoir computing: A new approach to optical information processing , 2010, 2010 12th International Conference on Transparent Optical Networks.

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

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