Performance Enhancement of a Delay-Based Reservoir Computing System by Using Gradient Boosting Technology

Gradient boosting technology has been proved to be an effective scheme for enhancing the performances of spatially distributed reservoir computing (RC) systems. In this work, a gradient boosting scheme by combining two reservoirs is proposed and numerically investigated in a delayed-based RC system. The original reservoir in the delayed-based RC system is a vertical-cavity surface-emitting laser (VCSEL) under polarization-rotated optical feedback (PR-OF), and it is trained on the desired output. The other VCSEL under PR-OF or polarization-preserved optical feedback (PP-OF) is supplemented to be an extra reservoir, which is trained on the remaining error of the original reservoir. Via Santa-Fe time series prediction task and 10th-order nonlinear autoregressive moving average (NARMA10) task, the performances of the delay-based RC system are evaluated before and after supplementing the extra reservoir, and then the effectiveness of the gradient boosting technology in the delayed RC system can be analyzed. The simulated results demonstrate that adopting gradient boosting technology is effective in a delay-based RC system. Comparatively speaking, the enhanced effect is more obvious under taking a VCSEL with PR-OF as the extra reservoir.

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

[2]  Damien Rontani,et al.  Enhanced performance of a reservoir computer using polarization dynamics in VCSELs. , 2018, Optics letters.

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

[4]  Jiangtao Xi,et al.  Optical chaotic flip-flop operations with multiple triggering under clock synchronization in the VCSEL with polarization-preserved optical injection. , 2020, Optics express.

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

[6]  YuShuang Hou,et al.  Parallel information processing by a reservoir computing system based on a VCSEL subject to double optical feedback and optical injection. , 2019, Optics express.

[7]  Hegui Zhu,et al.  Simultaneous recognition of two channels of optical packet headers utilizing reservoir computing subject to mutual-coupling optoelectronic feedback , 2018 .

[8]  Atsushi Uchida,et al.  Laser dynamical reservoir computing with consistency: an approach of a chaos mask signal. , 2016, Optics express.

[9]  Dan Wang,et al.  Prediction performance of reservoir computing system based on a semiconductor laser subject to double optical feedback and optical injection. , 2018, Optics express.

[10]  Lin Lin,et al.  Polarization Multiplexing Reservoir Computing Based on a VCSEL With Polarized Optical Feedback , 2020, IEEE Journal of Selected Topics in Quantum Electronics.

[11]  Yang Yi,et al.  A deep learning based approach for analog hardware implementation of delayed feedback reservoir computing system , 2018, 2018 19th International Symposium on Quality Electronic Design (ISQED).

[12]  Alexandre Locquet,et al.  Influence of polarization mode competition on the synchronization of two unidirectionally coupled vertical-cavity surface-emitting lasers. , 2007, Optics letters.

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

[14]  Atsushi Uchida,et al.  Reservoir Computing Using Multiple Lasers With Feedback on a Photonic Integrated Circuit , 2020, IEEE Journal of Selected Topics in Quantum Electronics.

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

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

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

[18]  Andrew Katumba,et al.  Improving Time Series Recognition and Prediction With Networks and Ensembles of Passive Photonic Reservoirs , 2020, IEEE Journal of Selected Topics in Quantum Electronics.

[19]  Wei Pan,et al.  Cascadable Neuron-Like Spiking Dynamics in Coupled VCSELs Subject to Orthogonally Polarized Optical Pulse Injection , 2017, IEEE Journal of Selected Topics in Quantum Electronics.

[20]  M. C. Soriano,et al.  Advances in photonic reservoir computing , 2017 .

[21]  K. Shore,et al.  VCSEL polarization control by optical injection , 2003 .

[22]  Xi-Rong Bao,et al.  A Multiple-Input Multiple-Output Reservoir Computing System Subject to Optoelectronic Feedbacks and Mutual Coupling , 2020, Entropy.

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

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

[25]  C. L. Philip Chen,et al.  Data-intensive applications, challenges, techniques and technologies: A survey on Big Data , 2014, Inf. Sci..

[26]  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.

[27]  Wei Pan,et al.  Enhanced chaotic communication in VCSELs with variable-polarization optical feedback and polarization-preserved optical injection , 2012 .

[28]  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.

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

[30]  Miguel C. Soriano,et al.  Comparison of Photonic Reservoir Computing Systems for Fiber Transmission Equalization , 2020, IEEE Journal of Selected Topics in Quantum Electronics.

[31]  Neal B. Abraham,et al.  Polarization properties of vertical-cavity surface-emitting lasers , 1997 .

[32]  Y. Hao,et al.  Four-channels reservoir computing based on polarization dynamics in mutually coupled VCSELs system. , 2019, Optics express.

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

[34]  Guy Van der Sande,et al.  Delay-Based Reservoir Computing Using Multimode Semiconductor Lasers: Exploiting the Rich Carrier Dynamics , 2019, IEEE Journal of Selected Topics in Quantum Electronics.

[35]  Romain Modeste Nguimdo,et al.  Reducing the phase sensitivity of laser-based optical reservoir computing systems. , 2016, Optics express.

[36]  Laurent Larger,et al.  Tutorial: Photonic Neural Networks in Delay Systems , 2018, Journal of Applied Physics.

[37]  Lin-Fu Li,et al.  Wideband Polarization-Resolved Chaos With Time-Delay Signature Suppression in VCSELs Subject to Dual Chaotic Optical Injections , 2018, IEEE Access.

[38]  Romain Modeste Nguimdo,et al.  Fast photonic information processing using semiconductor lasers with delayed optical feedback: role of phase dynamics. , 2014, Optics express.