One memristor-one electrolyte-gated transistor-based high energy-efficient dropout neuronal units

doi:10.1088/1674-1056/ad39d6

中国物理B ›› 2024, Vol. 33 ›› Issue (6): 68401-068401.doi: 10.1088/1674-1056/ad39d6

One memristor-one electrolyte-gated transistor-based high energy-efficient dropout neuronal units

Yalin Li(李亚霖)^1,†, Kailu Shi(时凯璐)^1,†, Yixin Zhu(朱一新)¹, Xiao Fang(方晓)¹, Hangyuan Cui(崔航源)¹, Qing Wan(万青)^2,‡, and Changjin Wan(万昌锦)^1,§

1 School of Electronic Science & Engineering, and Collaborative Innovation Center of Advanced Microstructures, Nanjing University, Nanjing 210023, China;
2 Yongjiang Laboratory (Y-LAB), Ningbo 315202, China

收稿日期:2024-03-08 修回日期:2024-03-19 接受日期:2024-04-03 出版日期:2024-06-18 发布日期:2024-06-18
通讯作者: Qing Wan, Changjin Wan E-mail:wanqing@nju.edu.cn;cjwan@nju.edu.cn
基金资助:
Project supported by the National Key Research and Development Program of China (Grant Nos. 2021YFA1202600 and 2023YFE0208600) and in part by the National Natural Science Foundation of China (Grant Nos. 62174082, 92364106, 61921005, 92364204, and 62074075).

One memristor-one electrolyte-gated transistor-based high energy-efficient dropout neuronal units

Yalin Li(李亚霖)^1,†, Kailu Shi(时凯璐)^1,†, Yixin Zhu(朱一新)¹, Xiao Fang(方晓)¹, Hangyuan Cui(崔航源)¹, Qing Wan(万青)^2,‡, and Changjin Wan(万昌锦)^1,§

1 School of Electronic Science & Engineering, and Collaborative Innovation Center of Advanced Microstructures, Nanjing University, Nanjing 210023, China;
2 Yongjiang Laboratory (Y-LAB), Ningbo 315202, China

Received:2024-03-08 Revised:2024-03-19 Accepted:2024-04-03 Online:2024-06-18 Published:2024-06-18
Contact: Qing Wan, Changjin Wan E-mail:wanqing@nju.edu.cn;cjwan@nju.edu.cn
Supported by:
Project supported by the National Key Research and Development Program of China (Grant Nos. 2021YFA1202600 and 2023YFE0208600) and in part by the National Natural Science Foundation of China (Grant Nos. 62174082, 92364106, 61921005, 92364204, and 62074075).

摘要/Abstract

摘要： Artificial neural networks (ANN) have been extensively researched due to their significant energy-saving benefits. Hardware implementations of ANN with dropout function would be able to avoid the overfitting problem. This letter reports a dropout neuronal unit (1R1T-DNU) based on one memristor-one electrolyte-gated transistor with an ultralow energy consumption of 25pJ/spike. A dropout neural network is constructed based on such a device and has been verified by MNIST dataset, demonstrating high recognition accuracies ($> 90$%) within a large range of dropout probabilities up to 40%. The running time can be reduced by increasing dropout probability without a significant loss in accuracy. Our results indicate the great potential of introducing such 1R1T-DNUs in full-hardware neural networks to enhance energy efficiency and to solve the overfitting problem.

关键词: dropout neuronal unit, synaptic transistors, memristor, artificial neural network

Abstract: Artificial neural networks (ANN) have been extensively researched due to their significant energy-saving benefits. Hardware implementations of ANN with dropout function would be able to avoid the overfitting problem. This letter reports a dropout neuronal unit (1R1T-DNU) based on one memristor-one electrolyte-gated transistor with an ultralow energy consumption of 25pJ/spike. A dropout neural network is constructed based on such a device and has been verified by MNIST dataset, demonstrating high recognition accuracies ($> 90$%) within a large range of dropout probabilities up to 40%. The running time can be reduced by increasing dropout probability without a significant loss in accuracy. Our results indicate the great potential of introducing such 1R1T-DNUs in full-hardware neural networks to enhance energy efficiency and to solve the overfitting problem.

Key words: dropout neuronal unit, synaptic transistors, memristor, artificial neural network

中图分类号: (Neural networks)

84.35.+i

73.40.Mr (Semiconductor-electrolyte contacts) 77.55.-g (Dielectric thin films) 81.05.Gc (Amorphous semiconductors)

Yalin Li(李亚霖), Kailu Shi(时凯璐), Yixin Zhu(朱一新), Xiao Fang(方晓), Hangyuan Cui(崔航源), Qing Wan(万青), and Changjin Wan(万昌锦). One memristor-one electrolyte-gated transistor-based high energy-efficient dropout neuronal units[J]. 中国物理B, 2024, 33(6): 68401-068401.

参考文献

[1] López C 2023 Advanced Materials 35 2208683
[2] Prezioso M, Merrikh-Bayat F, Hoskins B D, Adam G C, Likharev K K and Strukov D B 2015 Nature 521 61
[3] Ahn E C 2020 npj 2D Materials and Applications 4 17
[4] Sun K, Chen J and Yan X 2021 Adv. Funct. Mater. 31 2006773
[5] Zhu L Q, Wan C J, Guo L Q, Shi Y and Wan Q 2014 Nat. Commun. 5 3158
[6] Zhu Y, He Y, Chen C, Zhu L, Mao H, Zhu Y, Wang X, Yang Y, Wan C and Wan Q 2022 Appl. Phys. Lett. 120 113504
[7] Zhu Y, Peng B, Zhu L, Chen C, Wang X, Mao H, Zhu Y, Fu C, Ke S, Wan C and Wan Q 2022 Appl. Phys. Lett. 121 133502
[8] Lin X, Long H, Ke S, Wang Y, Zhu Y, Chen C, Wan C and Wan Q 2022 Chin. Phys. Lett. 39 068501
[9] Wu X, Zhang Y, Zhang T and Zhang B 2023 Chin. Phys. B 32 100506
[10] Xiang T, Chen F, Li X, Wang X, Yan Y and Wang L 2023 Chin. Phys. B 32 117301
[11] Yang Y, Fu C, Ke S, Cui H, Fang X, Wan C and Wan Q 2023 Chin. Phys. B 32 118101
[12] Amirsoleimani A, Alibart F, Yon V, Xu J, Pazhouhandeh M R, Ecoffey S, Beilliard Y, Genov R and Drouin D 2020 Advanced Intelligent Systems 2 2000115
[13] Demasius K U, Kirschen A and Parkin S 2021 Nat. Electron. 4 748
[14] Srivastava N, Hinton G, Krizhevsky A, Sutskever I and Salakhutdinov R 2014 Journal of Machine Learning Research 15 1929
[15] Huang H M, Xiao Y, Yang R, Yu Y T, He H K, Wang Z and Guo X 2020 Adv. Sci. 7 2001842
[16] Wang Z, Joshi S, Savel’ev S E, Jiang H, Midya R, Lin P, Hu M, Ge N, Strachan J P, Li Z, Wu Q, Barnell M, Li G L, Xin H L, Williams R S, Xia Q and Yang J J 2017 Nat. Mater. 16 101
[17] Wang Z, Wu H, Burr G W, Hwang C S, Wang K L, Xia Q and Yang J J 2020 Nat. Rev. Mater. 5 173
[18] Wan C, Zhou J, Shi Y and Wan Q 2014 IEEE Electron Dev. Lett. 35 414
[19] Wan X, Feng P, Wu G D, Shi Y and Wan Q 2015 IEEE Electron Dev. Lett. 36 204
[20] Shao F, Feng P, Wan C, Wan X, Yang Y, Shi Y and Wan Q 2017 Adv. Electron. Mater. 3 1600509
[21] Huang Q, Huang R, Pan Y, Tan S and Wang Y 2014 IEEE Electron Dev. Lett. 35 877
[22] Mazady A and Anwar M 2014 IEEE Trans. Electron Dev. 61 1054
[23] Sanjar K, Rehman A, Paul A and JeongHong K 2020 8th International Conference on Orange Technology (ICOT), 18-21 December, 2020, pp. 1-4
[24] Zhu Y, Peng B, Zhu L, Chen C, Wang X, Mao H, Zhu Y, Fu C, Ke S, Wan C and Wan Q 2022 Appl. Phys. Lett. 121 133502
[25] Mendenhall J and Meiler J 2016 Journal of Computer-Aided Molecular Design 30 177

One memristor-one electrolyte-gated transistor-based high energy-efficient dropout neuronal units

One memristor-one electrolyte-gated transistor-based high energy-efficient dropout neuronal units

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 15

Metrics

本文评价

推荐阅读 0

[1]	Xiao-Guang Shao(邵晓光), Jie Zhang(张捷), and Yan-Juan Lu(鲁延娟). Event-based nonfragile state estimation for memristive recurrent neural networks with stochastic cyber-attacks and sensor saturations[J]. 中国物理B, 2024, 33(7): 70203-070203.
[2]	Jingyue Wan(万婧玥), Fuqiang Wu(吴富强), Jun Ma(马军), and Wenshuai Wang(汪文帅). Dynamics and synchronization of neural models with memristive membranes under energy coupling[J]. 中国物理B, 2024, 33(5): 50504-050504.
[3]	Dawei Ding(丁大为), Yan Niu(牛炎), Hongwei Zhang(张红伟), Zongli Yang(杨宗立), Jin Wang(王金), Wei Wang(王威), and Mouyuan Wang(王谋媛). Fractional-order heterogeneous memristive Rulkov neuronal network and its medical image watermarking application[J]. 中国物理B, 2024, 33(5): 50503-050503.
[4]	Jieyu Lu(鲁婕妤), Xiaohua Xie(谢小华), Yaping Lu(卢亚平), Yalian Wu(吴亚联), Chunlai Li(李春来), and Minglin Ma(马铭磷). Dynamical behaviors in discrete memristor-coupled small-world neuronal networks[J]. 中国物理B, 2024, 33(4): 48701-048701.
[5]	Xinwei Zhou(周新卫), Donghua Jiang(蒋东华), Jean De Dieu Nkapkop, Musheer Ahmad, Jules Tagne Fossi, Nestor Tsafack, and Jianhua Wu(吴建华). Dynamics analysis and cryptographic implementation of a fractional-order memristive cellular neural network model[J]. 中国物理B, 2024, 33(4): 40506-040506.
[6]	Xiaoxia Li(李晓霞), Qianqian He(何倩倩), Tianyi Yu(余天意),Zhuang Cai(才壮), and Guizhi Xu(徐桂芝). Coexistence behavior of asymmetric attractors in hyperbolic-type memristive Hopfield neural network and its application in image encryption[J]. 中国物理B, 2024, 33(3): 30505-030505.
[7]	Minglin Ma(马铭磷), Kangling Xiong(熊康灵), Zhijun Li(李志军), and Shaobo He(贺少波). Dynamical behavior of memristor-coupled heterogeneous discrete neural networks with synaptic crosstalk[J]. 中国物理B, 2024, 33(2): 28706-028706.
[8]	Xun Yan(晏询), Zhijun Li(李志军), and Chunlai Li(李春来). Dynamics and synchronization in a memristor-coupled discrete heterogeneous neuron network considering noise[J]. 中国物理B, 2024, 33(2): 28705-028705.
[9]	Yi-Qun Li(李逸群), Jian Liu(刘坚), Chun-Biao Li(李春彪), Zhi-Feng Hao(郝志峰), and Xiao-Tong Zhang(张晓彤). Dynamical analysis, geometric control and digital hardware implementation of a complex-valued laser system with a locally active memristor[J]. 中国物理B, 2023, 32(8): 80503-080503.
[10]	Peiwen Tong(童霈文), Hui Xu(徐晖), Yi Sun(孙毅), Yongzhou Wang(汪泳州), Jie Peng(彭杰),Cen Liao(廖岑), Wei Wang(王伟), and Qingjiang Li(李清江). Lightweight and highly robust memristor-based hybrid neural networks for electroencephalogram signal processing[J]. 中国物理B, 2023, 32(7): 78505-078505.
[11]	Shu Wang(王姝), Tao Chen(陈涛), Yu Gong(龚钰), Fan Sun(孙帆), Si-Yuan Shen(申思远), Shu-Kai Duan(段书凯), and Li-Dan Wang(王丽丹). A progressive surrogate gradient learning for memristive spiking neural network[J]. 中国物理B, 2023, 32(6): 68704-068704.
[12]	Ming-Lin Ma(马铭磷), Xiao-Hua Xie(谢小华), Yang Yang(杨阳), Zhi-Jun Li(李志军), and Yi-Chuang Sun(孙义闯). Synchronization coexistence in a Rulkov neural network based on locally active discrete memristor[J]. 中国物理B, 2023, 32(5): 58701-058701.
[13]	Zhan-Hong Guo(郭展宏), Zhi-Jun Li(李志军), Meng-Jiao Wang(王梦蛟), and Ming-Lin Ma(马铭磷). Hopf bifurcation and phase synchronization in memristor-coupled Hindmarsh-Rose and FitzHugh-Nagumo neurons with two time delays[J]. 中国物理B, 2023, 32(3): 38701-038701.
[14]	Fan Sun(孙帆), Jing Su(粟静), Jie Li(李杰), Shukai Duan(段书凯), and Xiaofang Hu(胡小方). Memristor's characteristics: From non-ideal to ideal[J]. 中国物理B, 2023, 32(2): 28401-028401.
[15]	Yang Du(都洋), Guoqiang Long(隆国强), Donghua Jiang(蒋东华), Xiuli Chai(柴秀丽), and Junhe Han(韩俊鹤). Optical image encryption algorithm based on a new four-dimensional memristive hyperchaotic system and compressed sensing[J]. 中国物理B, 2023, 32(11): 114203-114203.