首页 > 论文 > 激光与光电子学进展 > 54卷 > 8期(pp:80005--1)

储备池计算硬件实现方案研究进展

Research Progress in Hardware Implementations of Reservoir Computing

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

储备池计算是一种适合处理时序信号的简单高效的机器学习算法。相比在传统电子计算机上用软件实现的方式, 储备池计算在光器件上的实现方式将更有利于超高速和超低功耗的信息处理。介绍了储备池计算的基本原理, 从输入层、储备池和输出层三个方面介绍了储备池计算硬件实现方案的研究进展, 指出了储备池计算硬件实现方案发展中存在的问题, 并展望了其未来发展趋势。

Abstract

Reservoir computing is a simple and effective machine learning algorithm to process time dependent signals. Compared with the software implementation in traditional electronic computer, reservoir computing implementation with optical components is more beneficial to information processing with ultrafast speed and ultralow power consumption. The basic principles of reservoir computing are presented, and the research progress in hardware implementation of reservoir computers is introduced from three aspects of input layer, reservoir and output layer. The existing problems in the development of the hardware implementation are demonstrated, and their future developing trends are discussed as well.

投稿润色
补充资料

中图分类号:TN29;N93;TP183

DOI:10.3788/lop54.080005

所属栏目:综述

基金项目:国家自然科学基金(61108004)、上海市浦江人才计划(14PJD017)、上海市特种光纤与光接入网重点实验室开放课题(SKLSFO2015-02)

收稿日期:2017-02-22

修改稿日期:2017-03-29

网络出版日期:--

作者单位    点击查看

李磊:上海大学特种光纤与光接入网省部共建重点实验室, 上海 200072上海大学通信与信息工程学院, 上海 200072
方捻:上海大学特种光纤与光接入网省部共建重点实验室, 上海 200072上海大学通信与信息工程学院, 上海 200072
王陆唐:上海大学特种光纤与光接入网省部共建重点实验室, 上海 200072上海大学通信与信息工程学院, 上海 200072
黄肇明:上海大学特种光纤与光接入网省部共建重点实验室, 上海 200072上海大学通信与信息工程学院, 上海 200072

联系人作者:李磊(13546720226@163.com)

备注:李磊(1989-), 男, 硕士研究生, 主要从事储备池计算软件算法和硬件实现方案方面的研究。

【1】Caulfield H J, Dolev S. Why future supercomputing requires optics[J]. Nature Photonics, 2010, 4(5): 261-263.

【2】Tucker R S. The role of optics in computing[J]. Nature Photonics, 2010, 4(7): 405.

【3】Woods D, Naughton T J. Optical computing: photonic neural networks[J]. Nature Physics, 2012, 8(4): 257-259.

【4】Jaeger H. The “Echo State” approach to analyzing and training recurrent neural network[R]. Bremen: GMD Report 148, GMD-German National Research Institute for Computer Science, 2001.

【5】Maass W, Natschlager T. Real-time computing without stable states:a new framework for neural computation based on perturbations[J]. Neural Computation, 2002, 14(11): 2531-2560.

【6】Verstraeten D, Schrauwen B, Stroobandt D. An experimental unification of reservoircomputing methods[J]. Neural Networks, 2007, 20(3): 391-403.

【7】Lukosevicius M, Jeager H. Reservoir computing approaches to recurrent neural network training[J]. Computer Science Review, 2009, 3(3): 127-149.

【8】Jaeger H, Haas H. Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication[J]. Science, 2004, 304(5667): 78-80.

【9】Verstraeten D, Schrauwen B, Stroobandt D, et al. Isolated word recognition with the liquid state machine: a case study[J]. Information Processing Letters, 2005, 95(6): 521-528.

【10】Triefenbach F, Jalalvand A, Schrauwen B, et al. Phoneme recognition with large hierarchical reservoirs[C]. Proceedings of Advances in Neural Information Processing Systems, 2010, 23: 2307-2315.

【11】Joshi P, Maass W. Movement generation and control with generic neural microcircuits[C]. 1st International Workshop on Biologically Inspired Approaches to Advanced Information Technology, 2004, 3141: 258-273.

【12】The 2006/07 forecasting competition for neural networks & computational intelligence (2006)[EB/OL]. http://www.neural-forecasting-competition.com/NN3/.

【13】Appeltant L, Soriano M C, Danckaret J, et al. Information processing using a single dynamical node as complex system[J]. Nature Communications, 2011, 2(9): 468.

【14】Vandoorne K, Dierckx W, Schrauwen B, et al. Toward optical signal processing using photonic reservoir computing[J]. Optics Express, 2008, 16(15): 11182-11192.

【15】Vandoorne K, Dambre J, Verstraeten D, et al. Parallel reservoir computing using optical amplifiers[J]. IEEE Transactions on Neural Networks, 2011, 22(9): 1469-1481.

【16】Vandoorne K, Mechet P, Vaerenbergh T V, et al. Experimental demonstration of reservoir computing on a silicon photonics chip[J]. Nature Communications, 2014, 5(5): 3541.

【17】Schneider B, Dambre J, Bienstman P. Using digital masks to enhance the bandwidth tolerance and improve the performance of on-chip reservoir computing systems[J]. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(12): 2748-2753.

【18】Simpson T B, Liu J M, Almulla M, et al. Linewidth sharpening via polarization-rotated feedback in optically injected semiconductor laser oscillators[J]. IEEE Journal of Selected Topics in Quantum Electronics, 2013, 19(4): 1500807.

【19】Wei B, Wu Z M, Deng T, et al. Nonlinear dynamics of 1550 nm VCSELs subject to polarization-preserved optical feedback and orthogonal optical injection[J]. Frontiers of Optoelectronics, 2013, 6(3): 243-250.

【20】Jiang X X, Cheng M F, Luo F G, et al. Electro-optic chaotic system based on the reverse-time chaos theory and a nonlinear hybrid feedback loop[J]. Optics Express, 2016, 24(25): 28804-28814.

【21】Xiong Xiaozhi, Fang Nian, Wang Lutang, et al. Multi-switch states detection system based on semiconductor laser with optical feedbacks[J]. Acta Photonica Sinica, 2017, 46(3): 0314003.
熊小志, 方 捻, 王陆唐, 等. 基于光反馈半导体激光器的多开关状态检测系统[J]. 光子学报, 2017, 46(3): 0314003.

【22】Aghababa M P, Sharif J A. Chaos and complexity in mine grade distribution series detected by nonlinear approaches[J]. Complexity, 2016, 21(S2): 355-369.

【23】Fang N, Wang L T, Guo S Q, et al. Security of polarization-shift keying chaos optical communication system[J]. Frontiers of Optoelectronics in China, 2008, 1(1): 64-69.

【24】Qin Haijuan, Fang Nian, Wang Lutang, et al. Experimental investigation of adjacent-frame similarity of bidirectional optical fiber ring chaotic laser[J]. Laser & Optoelectronics Progress, 2014, 51(8): 081402.
秦海娟, 方 捻, 王陆唐, 等. 双向光纤环形混沌激光器相邻帧相似性的实验研究[J]. 激光与光电子学进展, 2014, 51(8): 081402.

【25】Liu C, Fang N, Wang L T, et al. Similarity of adjacent-frame chaos waveforms from semiconductor fiber ring laser in sensing applications[C]. SPIE, 2012, 8554: 85540L.

【26】Paquot Y, Duport F, Smerieri A, et al. Optoelectronic reservoir computing[J]. Scientific Reports, 2012, 2: 287.

【27】Larger L, Soriano M C, Brunner D, et al. Photonic information processing beyond turing: an optoelectronic implementation of reservoir computing[J]. Optics Express, 2012, 20(3): 3241-3249.

【28】Duport F, Schneider B, Semerieri A, et al. All-optical reservoir computing[J]. Optics Express, 2012, 20(20): 22783-22795.

【29】Soriano M C, Ortin S, Brunner D. et al. Optoelectronic reservoir computing tackling noise-induced performance degradation[J]. Optics Express, 2013, 21(1): 12-20.

【30】Appeltant L, Van der Sande G, Danckaert J, et al. Constructing optimized binary masks for reservoir computing with delay systems[J]. Scientific Reports, 2014, 4: 3629.

【31】Duport F, Akrout A, Smerieri A, et al. Analog input layer for optical reservoir computers[J]. Eprint Arxiv, 2014, 146: 460-464.

【32】Nakayama J, Kanno K, Uchida A. Laser dynamical reservoir computing with consistency: an approach of a chaos mask signal[J]. Optics Express, 2016, 24(8): 8679-8692.

【33】Tezuka M, Kanno K, Bunsen M. Reservoir computing with a slowly modulated mask signal for preprocessing using a mutually coupled optoelectronic system[J]. Japanese Journal of Applied Physics, 2016, 55(8): 08RE06.

【34】Brunner D, Soriano M C, Mirasso C R, et al. Parallel photonic information processing at gigabyte per second data rates using transient states[J]. Nature Communications, 2013, 4: 1364.

【35】Hicke K, Angel E M, Brunner D, et al. Informationprocessing using transient dynamics of semiconductor lasers subject to delayed feedback[J]. IEEE Journal of Selected Topics in Quantum Electronics, 2013, 19(4): 1501610.

【36】Nguimdo R M, Verschaffelt G, Danckaert J, et al. Fast photonic information processing using semiconductor lasers with delayed optical feedback: role of phase dynamics[J]. Optics Express, 2014, 22(7): 8672-8686.

【37】Zhang H, Feng X, Li B, et al. Integrated photonic reservoir computing based on hierarchical time-multiplexing structure[J]. Optics Express, 2014, 22(25): 31356-31370.

【38】Nguimdo R M, Verschaffelt G, Danckaert J, et al. Simultaneous computation of two independent tasks using reservoir computing based on a single photonic nonlinear node with optical feedback[J]. IEEE Transactions on Neural Networks and Learning Systems, 2015, 26(12): 3301-3307.

【39】Dejonckheere A, Duport F, Smerieri A, et al. All-optical reservoir computer based on saturation of absorption[J]. Optics Express, 2014, 22(9): 10868-10881.

【40】Vinckier Q, Duport F, Semerieri A, et al. High-performance photonic reservoir computer based on a coherently driven passive cavity[J]. Optica, 2015, 2(5): 438-446.

【41】Smerieri A, Duport F, Paquot Y, et al. Analog readout for optical reservoir computers[J]. Advances in Neural Information Processing Systems, 2012, 25: 953-961.

【42】Duport F, Smerieri A, Akrout A, et al. Fully analogue photonic reservoir computer[J]. Scientific Reports, 2016, 6: 22381.

【43】Nguimdo R M, Lacot E, Jacquin O, et al. Prediction performance of reservoir computing systems based on a diode-pumped erbium-doped microchip laser subject to optical feedback[J]. Optics Letters, 2017, 42(3): 375-378.

【44】Antonik P, Duport F, Smerieri A, et al. Online training of an opto-electronic reservoir computer[C]. Proceedings of International Conference on Neural Information Processing, 2015: 233-240.

【45】Haynes N D, Soriano M C, Rosin D P, et al. Reservoir computing with a single time-delay autonomous boolean node[J]. Physical Review E, 2015, 91(2): 020801.

【46】Zhao Qingchun, Yin Hongxi. Research progress of reservoir computing using chaotic laser[J]. Laser & Optoelectronics Progress, 2013, 50(3): 030003.
赵清春, 殷洪玺. 混沌光子储备池计算研究进展[J]. 激光与光电子学进展, 2013, 50(3): 030003.

【47】Bao Xiurong. Research progress in optoelectronic reservoir computing system[J]. Laser & Optoelectronics Progress, 2015, 52(3): 030005.
包秀荣. 光电储备池计算系统研究进展[J]. 激光与光电子学进展, 2015, 52(3): 030005.

【48】Soriano M C. Viewpoint: reservoir computing speeds up[J]. Physics Review X, 2017, 7: 011015.

引用该论文

Li Lei,Fang Nian,Wang Lutang,Huang Zhaoming. Research Progress in Hardware Implementations of Reservoir Computing[J]. Laser & Optoelectronics Progress, 2017, 54(8): 080005

李磊,方捻,王陆唐,黄肇明. 储备池计算硬件实现方案研究进展[J]. 激光与光电子学进展, 2017, 54(8): 080005

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF