Exploring reservoir computing: Implementation via double stochastic nanowire networks

doi:10.1088/1674-1056/aceeea

中国物理B ›› 2024, Vol. 33 ›› Issue (3): 37302-037302.doi: 10.1088/1674-1056/aceeea

Exploring reservoir computing: Implementation via double stochastic nanowire networks

Jian-Feng Tang(唐健峰)^1,6, Lei Xia(夏磊)¹, Guang-Li Li(李广隶)¹, Jun Fu(付军)¹, Shukai Duan(段书凯)^1,3,4, and Lidan Wang(王丽丹)^{1,2,3,5,6,†}

1 College of Artificial Intelligence, Southwest University, Chongqing 400715, China;
2 Brain-inspired Computing & Intelligent Control of Chongqing Key Laboratory, Chongqing 400715, China;
3 National & Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology, Chongqing 400715, China;
4 Chongqing Brain Science Collaborative Innovation Center, Chongqing 400715, China;
5 Key Laboratory of Luminescence Analysis and Molecular Sensing, Ministry of Education, Southwest University, Chongqing 400715, China;
6 State Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing 400715, China

收稿日期:2023-07-03 修回日期:2023-08-06 接受日期:2023-08-10 出版日期:2024-02-22 发布日期:2024-02-22
通讯作者: Lidan Wang E-mail:ldwang@swu.edu.cn
基金资助:
Project supported by the National Natural Science Foundation of China (Grant Nos. U20A20227,62076208, and 62076207), Chongqing Talent Plan ”Contract System” Project (Grant No. CQYC20210302257), National Key Laboratory of Smart Vehicle Safety Technology Open Fund Project (Grant No. IVSTSKL-202309), the Chongqing Technology Innovation and Application Development Special Major Project (Grant No. CSTB2023TIAD-STX0020), College of Artificial Intelligence, Southwest University, and State Key Laboratory of Intelligent Vehicle Safety Technology.

Exploring reservoir computing: Implementation via double stochastic nanowire networks

Jian-Feng Tang(唐健峰)^1,6, Lei Xia(夏磊)¹, Guang-Li Li(李广隶)¹, Jun Fu(付军)¹, Shukai Duan(段书凯)^1,3,4, and Lidan Wang(王丽丹)^{1,2,3,5,6,†}

1 College of Artificial Intelligence, Southwest University, Chongqing 400715, China;
2 Brain-inspired Computing & Intelligent Control of Chongqing Key Laboratory, Chongqing 400715, China;
3 National & Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology, Chongqing 400715, China;
4 Chongqing Brain Science Collaborative Innovation Center, Chongqing 400715, China;
5 Key Laboratory of Luminescence Analysis and Molecular Sensing, Ministry of Education, Southwest University, Chongqing 400715, China;
6 State Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing 400715, China

Received:2023-07-03 Revised:2023-08-06 Accepted:2023-08-10 Online:2024-02-22 Published:2024-02-22
Contact: Lidan Wang E-mail:ldwang@swu.edu.cn
Supported by:
Project supported by the National Natural Science Foundation of China (Grant Nos. U20A20227,62076208, and 62076207), Chongqing Talent Plan ”Contract System” Project (Grant No. CQYC20210302257), National Key Laboratory of Smart Vehicle Safety Technology Open Fund Project (Grant No. IVSTSKL-202309), the Chongqing Technology Innovation and Application Development Special Major Project (Grant No. CSTB2023TIAD-STX0020), College of Artificial Intelligence, Southwest University, and State Key Laboratory of Intelligent Vehicle Safety Technology.

摘要/Abstract

摘要： Neuromorphic computing, inspired by the human brain, uses memristor devices for complex tasks. Recent studies show that self-organizing random nanowires can implement neuromorphic information processing, enabling data analysis. This paper presents a model based on these nanowire networks, with an improved conductance variation profile. We suggest using these networks for temporal information processing via a reservoir computing scheme and propose an efficient data encoding method using voltage pulses. The nanowire network layer generates dynamic behaviors for pulse voltages, allowing time series prediction analysis. Our experiment uses a double stochastic nanowire network architecture for processing multiple input signals, outperforming traditional reservoir computing in terms of fewer nodes, enriched dynamics and improved prediction accuracy. Experimental results confirm the high accuracy of this architecture on multiple real-time series datasets, making neuromorphic nanowire networks promising for physical implementation of reservoir computing.

关键词: double-layer stochastic (DS) nanowire network architecture, neuromorphic computation, nanowire network, reservoir computing, time series prediction

Abstract: Neuromorphic computing, inspired by the human brain, uses memristor devices for complex tasks. Recent studies show that self-organizing random nanowires can implement neuromorphic information processing, enabling data analysis. This paper presents a model based on these nanowire networks, with an improved conductance variation profile. We suggest using these networks for temporal information processing via a reservoir computing scheme and propose an efficient data encoding method using voltage pulses. The nanowire network layer generates dynamic behaviors for pulse voltages, allowing time series prediction analysis. Our experiment uses a double stochastic nanowire network architecture for processing multiple input signals, outperforming traditional reservoir computing in terms of fewer nodes, enriched dynamics and improved prediction accuracy. Experimental results confirm the high accuracy of this architecture on multiple real-time series datasets, making neuromorphic nanowire networks promising for physical implementation of reservoir computing.

Key words: double-layer stochastic (DS) nanowire network architecture, neuromorphic computation, nanowire network, reservoir computing, time series prediction

中图分类号: (Electronic transport in nanoscale materials and structures)

73.63.-b

05.45.-a (Nonlinear dynamics and chaos)

Jian-Feng Tang(唐健峰), Lei Xia(夏磊), Guang-Li Li(李广隶), Jun Fu(付军), Shukai Duan(段书凯), and Lidan Wang(王丽丹). Exploring reservoir computing: Implementation via double stochastic nanowire networks[J]. 中国物理B, 2024, 33(3): 37302-037302.

参考文献

[1] Upadhyay N K, Jiang H, Wang Z, Asapu S, Xia Q and Joshua Yang J 2019 Advanced Materials Technologies 4 1800589
[2] Yang J J, Pickett M D, Li X, Ohlberg D A, Stewart D R and Williams R S 2008 Nat. Nanotechnol. 3 429
[3] Wang Z, Joshi S, Savel'ev S E, Jiang H, Midya R, Lin P, Hu M, Ge N, Strachan J P, Li Z, et al. 2017 Nat. Mater. 16 101
[4] Sun L, Wang Z, Jiang J, Kim Y, Joo B, Zheng S, Lee S, Yu W J, Kong B S and Yang H 2021 Science Advances 7 eabg1455
[5] Moon J, Ma W, Shin J H, Cai F, Du C, Lee S H and Lu W D 2019 Nat. Electron. 2 480
[6] Lao J, Yan M, Tian B, Jiang C, Luo C, Xie Z, Zhu Q, Bao Z, Zhong N, Tang X, et al. 2022 Advanced Science 9 2106092
[7] Christensen D V, Dittmann R, Linares-Barranco B, Sebastian A, Le Gallo M, Redaelli A, Slesazeck S, Mikolajick T, Spiga S, Menzel S, et al. 2022 Neuromorphic Computing and Engineering 2 022501
[8] Xia Q and Yang J J 2019 Nat. Mater. 18 309
[9] Zhu R, Hochstetter J, Loeffler A, Diaz-Alvarez A, Nakayama T, Lizier J T and Kuncic Z 2021 Scientific Reports 11 1
[10] Mallinson J, Shirai S, Acharya S, Bose S, Galli E and Brown S 2019 Science Advances 5 eaaw8438
[11] Hochstetter J, Zhu R, Loeffler A, Diaz-Alvarez A, Nakayama T and Kuncic Z 2021 Nat. Commun. 12 1
[12] Scharnhorst K S, Carbajal J P, Aguilera R C, Sandouk E J, Aono M, Stieg A Z and Gimzewski J K 2018 Jpn. J. Appl. Phys. 57 03ED02
[13] Milano G, Pedretti G, Montano K, Ricci S, Hashemkhani S, Boarino L, Ielmini D and Ricciardi C 2022 Nat. Mater. 21 195
[14] Fu K, Zhu R, Loeffler A, Hochstetter J, Diaz-Alvarez A, Stieg A, Gimzewski J, Nakayama T and Kuncic Z 2020 Reservoir computing with neuromemristive nanowire networks 2020 International Joint Conference on Neural Networks (IJCNN) (IEEE) pp. 1-8
[15] Lilak S, Woods W, Scharnhorst K, Dunham C, Teuscher C, Stieg A Z and Gimzewski J K 2021 Frontiers in Nanotechnology 3 675792
[16] Schrauwen B, Verstraeten D and Van Campenhout J 2007 An overview of reservoir computing: theory, applications and implementations Proceedings of the 15th european symposium on artificial neural networks pp. 471-482 2007 pp. 471-482
[17] Milano G, Pedretti G, Fretto M, Boarino L, Benfenati F, Ielmini D, Valov I and Ricciardi C 2020 Advanced Intelligent Systems 2 2000096
[18] Tanaka H, Akai-Kasaya M, TermehYousefi A, Hong L, Fu L, Tamukoh H, Tanaka D, Asai T and Ogawa T 2018 Nat. Commun. 9 1
[19] Shirai S, Acharya S K, Bose S K, Mallinson J B, Galli E, Pike M D, Arnold M D and Brown S A 2020 Network Neuroscience 4 432
[20] Diaz-Alvarez A, Higuchi R, Sanz-Leon P, Marcus I, Shingaya Y, Stieg A Z, Gimzewski J K, Kuncic Z and Nakayama T 2019 Scientific Reports 9 1
[21] Montano K, Milano G and Ricciardi C 2022 Neuromorphic Computing and Engineering 2 014007
[22] Zegarac A and Caravelli F 2019 Europhys. Lett. 125 10001
[23] Milano G, Miranda E and Ricciardi C 2022 Neural Networks 150 137
[24] Menzel S, Tappertzhofen S, Waser R and Valov I 2013 Physical Chemistry Chemical Physics 15 6945
[25] Citri A and Malenka R C 2008 Neuropsychopharmacology 33 18
[26] Rodriguez-Fernandez A, Cagli C, Suñé J and Miranda E 2018 IEEE Electron. Device Lett. 39 656
[27] Miranda E, Milano G and Ricciardi C 2020 IEEE Transactions on Nanotechnology 19 609
[28] Li Q, Diaz-Alvarez A, Iguchi R, Hochstetter J, Loeffler A, Zhu R, Shingaya Y, Kuncic Z, Uchida K I and Nakayama T 2020 Advanced Functional Materials 30 2003679
[29] Manning H G, Niosi F, da Rocha C G, Bellew A T, O'Callaghan C, Biswas S, Flowers P F, Wiley B J, Holmes J D, Ferreira M S, et al. 2018 Nat. Commun. 9 1
[30] Sun J, Li L and Peng H 2021 An image classification method based on echo state network 2021 International Conference on Neuromorphic Computing (ICNC) (IEEE) pp. 165-170
[31] Gao R, Du L, Duru O and Yuen K F 2021 Applied Soft Computing 102 107111
[32] Li D, Han M and Wang J 2012 IEEE Transactions on Neural Networks and Learning Systems 23 787
[33] Jaeger H 2002 Advances in neural information processing systems 15
[34] Song Z, Wu K and Shao J 2020 Neurocomputing 406 343
[35] Shi G, Liu D and Wei Q 2016 Neurocomputing 216 478
[36] Skowronski M D and Harris J G 2006 Minimum mean squared error time series classification using an echo state network prediction model 2006 IEEE International Symposium on Circuits and Systems (IEEE) pp. 3153-3156
[37] Lin X, Yang Z and Song Y 2009 Expert Systems with Applications 36 7313
[38] Gallicchio C, Micheli A and Pedrelli L 2017 Deep reservoir computing: A critical experimental analysis. Neurocomputing, 268 pp. 87-99
[39] Lukoševičius M and Jaeger H 2009 Computer science review 3 127
[40] Sun C, Song M, Cai D, et al. 2022 A Systematic Review of Echo State Networks from Design to Application IEEE Transactions on Artificial Intelligence, 2022. pp. 23-37
[41] Stolfi D H, Alba E and Yao X 2017 Predicting car park occupancy rates in smart cities International Conference on Smart Cities (Springer) pp, 107-117
[42] Fanaee-T H and Gama J 2014 Progress in Artificial Intelligence 2 113
[43] Jaeger H and Haas H 2004 Science 304 78
[44] Shi Z and Han M 2007 IEEE Transactions on Neural Networks 18 359
[45] Sorjamaa A, Hao J, Reyhani N, Ji Y and Lendasse A 2007 Neurocomputing 70 2861
[46] Xu M and Han M 2016 IEEE Transactions on Cybernetics 46 2173

Exploring reservoir computing: Implementation via double stochastic nanowire networks

Exploring reservoir computing: Implementation via double stochastic nanowire networks

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

Metrics

本文评价

推荐阅读 0

[1]	Dong-Zhou Zhong(钟东洲), Zhe Xu(徐喆), Ya-Lan Hu(胡亚兰), Ke-Ke Zhao(赵可可), Jin-Bo Zhang(张金波),Peng Hou(侯鹏), Wan-An Deng(邓万安), and Jiang-Tao Xi(习江涛). Multi-target ranging using an optical reservoir computing approach in the laterally coupled semiconductor lasers with self-feedback[J]. 中国物理B, 2022, 31(7): 74205-074205.
[2]	Tong-Feng Weng(翁同峰), Xin-Xin Cao(曹欣欣), and Hui-Jie Yang(杨会杰). Complex network perspective on modelling chaotic systems via machine learning[J]. 中国物理B, 2021, 30(6): 60506-060506.
[3]	钟剑, 董钢, 孙一妹, 张钊扬, 吴玉琴. Application of the nonlinear time series prediction method of genetic algorithm for forecasting surface wind of point station in the South China Sea with scatterometer observations[J]. 中国物理B, 2016, 25(11): 110502-110502.
[4]	刘涵, 刘丁, 邓凌峰. Chaotic time series prediction using fuzzy sigmoid kernel-based support vector machines[J]. 中国物理B, 2006, 15(6): 1196-1200.
[5]	叶美盈, 汪晓东. Chaotic time series prediction using least squares support vector machines[J]. 中国物理B, 2004, 13(4): 454-458.