Handwritten numeral recognition utilizing optoelectronic reservoir computing with double reservoir layers

Optoelectronic reservoir computing (RC) is a supervised training algorithm implanted in an optoelectronic time-delay system, which possesses simple structure and can be utilized to realize pattern recognition. In this work, based on double reservoir layers composed of two Mach-Zehnder modulators (MZMs), a novel optoelectronic RC system is proposed and the system performances for processing handwritten numeral recognition (HNR) are analyzed. For such a system, a masked handwritten numeral information is injected into the first reservoir layer, the different value between two adjacent node states of the first reservoir layer is sent to the second reservoir layer, and the virtual node states of the second reservoir layer are extracted for training and testing. The simulated results show that, by optimizing the system parameters, a word error rate (WER) of 0.11 for processing HNR can be achieved. By comparing with an optoelectronic RC with a single reservoir layer, the optoelectronic RC with two reservoir layers possesses better performances for processing HNR.

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

[2]  Zhao Yang,et al.  Reservoir computing system with double optoelectronic feedback loops. , 2019, Optics express.

[3]  Peng Xi-yuan.  Survey on Reservoir Computing , 2011 .

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

[5]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  Yu Jin,et al.  Handwritten numeral recognition utilizing reservoir computing subject to optoelectronic feedback , 2015, 2015 11th International Conference on Natural Computation (ICNC).

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

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

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

[10]  Yu Jin,et al.  Numerical Simulation and Experiment on Optical Packet Header Recognition Utilizing Reservoir Computing Based on Optoelectronic Feedback , 2017, IEEE Photonics Journal.

[11]  Zheng-Mao Wu,et al.  Performance optimization research of reservoir computing system based on an optical feedback semiconductor laser under electrical information injection. , 2019, Optics express.

[12]  Razvan Pascanu,et al.  How to Construct Deep Recurrent Neural Networks , 2013, ICLR.

[13]  Eckehard Schöll,et al.  Broadband chaos generated by an optoelectronic oscillator. , 2009, Physical review letters.

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

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

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

[17]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[18]  Damien Rontani,et al.  Large-Scale Spatiotemporal Photonic Reservoir Computer for Image Classification , 2020, IEEE Journal of Selected Topics in Quantum Electronics.