|
|
|
Memristor-based multi-synaptic spiking neuron circuit for spiking neural network |
| Wenwu Jiang(蒋文武)1, Jie Li(李杰)1, Hongbo Liu(刘洪波)1, Xicong Qian(钱曦聪)1, Yuan Ge(葛源)1, Lidan Wang(王丽丹)1,2,3,4, and Shukai Duan(段书凯)1,2,3,4,† |
1 College of Artificial Intelligence, Southwest University, Chongqing 400715, China;
2 National&Local Joint Engineering Laboratory of Intelligent Transmission and Control Technology, Chongqing 400715, China;
3 Brain-inspired Computing and Intelligent Control of Chongqing Key Laboratory, Chongqing 400715, China;
4 Chongqing Brain Science Collaborative Innovation Center, Chongqing 400715, China |
|
|
|
|
Abstract Spiking neural networks (SNNs) are widely used in many fields because they work closer to biological neurons. However, due to its computational complexity, many SNNs implementations are limited to computer programs. First, this paper proposes a multi-synaptic circuit (MSC) based on memristor, which realizes the multi-synapse connection between neurons and the multi-delay transmission of pulse signals. The synapse circuit participates in the calculation of the network while transmitting the pulse signal, and completes the complex calculations on the software with hardware. Secondly, a new spiking neuron circuit based on the leaky integrate-and-fire (LIF) model is designed in this paper. The amplitude and width of the pulse emitted by the spiking neuron circuit can be adjusted as required. The combination of spiking neuron circuit and MSC forms the multi-synaptic spiking neuron (MSSN). The MSSN was simulated in PSPICE and the expected result was obtained, which verified the feasibility of the circuit. Finally, a small SNN was designed based on the mathematical model of MSSN. After the SNN is trained and optimized, it obtains a good accuracy in the classification of the IRIS-dataset, which verifies the practicability of the design in the network.
|
Received: 25 June 2021
Revised: 12 August 2021
Accepted manuscript online: 10 November 2021
|
|
PACS:
|
07.50.Ek
|
(Circuits and circuit components)
|
| |
07.05.Mh
|
(Neural networks, fuzzy logic, artificial intelligence)
|
| |
84.32.-y
|
(Passive circuit components)
|
|
| Fund: Project supported by the National Key Research and Development Program of China (Grant No. 2018YFB1306600), the National Natural Science Foundation of China (Grant Nos. 62076207, 62076208, and U20A20227), and the Science and Technology Plan Program of Yubei District of Chongqing (Grant No. 2021-17). |
Corresponding Authors:
Shukai Duan
E-mail: duansk@swu.edu.cn
|
Cite this article:
Wenwu Jiang(蒋文武), Jie Li(李杰), Hongbo Liu(刘洪波), Xicong Qian(钱曦聪), Yuan Ge(葛源), Lidan Wang(王丽丹), and Shukai Duan(段书凯) Memristor-based multi-synaptic spiking neuron circuit for spiking neural network 2022 Chin. Phys. B 31 040702
|
[1] Schmidhuber J 2015 Neural Netw. 61 85
[2] Silver D, Huang A, Maddison C J, Guez A, Sifre L, van den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M, Dieleman S, Grewe D, Nham J, Kalchbrenner N, Sutskever I, Lillicrap T, Leach M, Kavukcuoglu K, Graepel T and Hassabis D 2016 Nature 529 484
[3] Krizhevsky A, Sutskever I and Hinton G E 2017 Commun. ACM 60 84
[4] Shin H C, Roth H R, Gao M C, Lu L, Xu Z Y, Nogues I, Yao J H, Mollura D and Summers R M 2016 IEEE Trans. Med. Imaging 35 1285
[5] Maass W 1997 Transactions of the Society for Computer Simulation International 14 1659
[6] Roy K, Jaiswal A and Panda P 2019 Nature 575 607
[7] Chua L O 1971 IEEE Transactions on Circuit Theory CT18 507
[8] Strukov D B, Snider G S, Stewart D R and Williams R S 2008 Nature 453 80
[9] Jiang W, Xie B, Liu C C and Shi Y 2019 Nature Electronics 2 376
[10] Jo S H, Chang T, Ebong I, Bhadviya B B, Mazumder P and Lu W 2010 Nano Lett. 10 1297
[11] Kim H 2012 Proc. IEEE 100 2061
[12] Wu X, Saxena V and Kehan Z 2015 Proceedings of the International Joint Conference on Neural Networks, July 12-17, 2015, Killarney, Ireland, p. 1
[13] Liu H J, Chen C L, Zhu X, Sun S Y, Li Q J and Li Z W 2020 Chin. Phys. B 29 028502
[14] Kim K, Park S, Hu S M, Song J, Lim W, Jeong Y, Kim J, Lee S, Kwak J Y, Park J, Park J K, Ju B K, Jeong D S and Kim I 2020 Npg Asia Materials 77 13
[15] Howard G, Gale E, Bull L, Costello B d L and Adamatzky A 2012 IEEE Transactions on Evolutionary Computation 16 711
[16] Liu Y D and Wang L M 2014 Acta Phys. Sin. 63 080503 (in Chinese)
[17] Hu M, Chen Y R, Yang J J, Wang Y and Li H 2017 IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 36 1353
[18] Zayer F, Dghais W, Benabdeladhim M and Hamdi B 2019 AEU-Int. J. Electron. Commun. 100 56
[19] Hajiabadi Z and Shalchian M 2021 J. Comput. Electron. 20 1625
[20] Hodgkin A L and Huxley A F 1952 J. Physiol.-London 117 500
[21] Izhikevich E M 2003 IEEE Transactions on Neural Networks 14 1569
[22] Brette R 2005 Journal of Neurophysiology 94 3637
[23] Ohtani T and Saito T 2008 IEICE Trans. Fundamentals 91 891
[24] Cruz-Albrecht J M 2012 IEEE Transactions on Biomedical Circuits & Systems 6 246
[25] Afifi A, Ayatollahi A, Raissi F and Hajghassem H 2010 IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences E93A 1670
[26] Babacan Y, Kacar B and Gurkan K 2016 Neurocomputing 203 86
[27] Kim T, Oh M H, Kwon M W and Park B G 2018 Electron. Lett. 54 1022
[28] Zhao L, Hong Q H, Wang X P 2018 Neurocomputing 314 207
[29] Woo S, Cho J, Lim D, Park Y S, Cho K and Kim S 2020 IEEE Trans. Electron Dev. 67 2995
[30] Serb A, Bill J, Khiat A, Berdan R, Legenstein R and Prodromakis T 2016 Nat. Commun. 7 12611
[31] Peng Y, Wu H, Gao B, Eryilmaz S B and Qian H 2017 Nat. Commun. 8 15199
[32] Hu M, Graves C E, Li C, Li Y N, Ge N, Montgomery E, Davila N, Jiang H, Williams R S, Yang J J S, Xia Q F and Strachan J P 2018 Adv. Mater. 30 1705914
[33] Li C, Wang Z, Rao M, Belkin D, Song W, Jiang H, Yan P, Li Y, Lin P and Hu M 2019 Nature Machine Intelligence 1 49
[34] Cai F X, Correll J M, Lee S H, Lim Y, Bothra V, Zhang Z Y, Flynn M P and Lu W D 2019 Nature Electronics 2 290
[35] Yao P, Wu H Q, Gao B, Tang J S, Zhang Q T, Zhang W Q, Yang J J and Qian H 2020 Nature 577 641
[36] Chen Y and Wang X 2009 Proceedings of the IEEE/ACM International Symposium on Nanoscale Architectures, July 30-31, 2009, San Francisco, CA, USA, p. 7
[37] Yong T, Nyengaard J R, Groot D and Gundersen H 2010 Synapse 41 258
[38] Aleksander I 2004 Nature 432 18
[39] Natschlager T and Ruf B 1998 Network-Computation in Neural Systems 9 319
[40] Fauth M, Worgotter F and Tetzlaff C 2015 PLoS Comput. Biol. 11 e1004031
[41] Bohte S M, Kok J N and La Poutre H 2002 Neurocomputing 48 Pii s0925-2312(01)00658-0 17 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
