Please wait a minute...
Journal of Integrative Neuroscience  2018, Vol. 17 Issue (4): 307-311    DOI: 10.31083/j.jin.2018.04.0407
Research article | Next articles
Anti-interference ability of deep spiking neural network
Lei Guo1, 2, 3, *(), Hongyi Shi1, 2, 3, Yunge Chen1, 2, 3, Hongli Yu1, 2, 3
1 Department of Biomedical Engineering, College of Electrical Engineering, Hebei University of Technology, 300130, Tianjin, China
2 State Key Laboratory of Reliable and Intelligence of Electrical Equipment, School of Electrical Engineering, Hebei University of Technology, 300130, Tianjin, China
3 Key Laboratory of Electromagnetic Field and Electrical Apparatus Reliability of Hebei Province, School of Electrical Engineering, Hebei University of Technology, 300130, Tianjin, China
Download:  PDF(826KB)  ( 462 ) Full text   ( 273 )
Export:  BibTeX | EndNote (RIS)      
Abstract  

Organisms have the advantages of self-adaptive mechanisms and an anti-interference ability. To investigate the anti-interference ability of a deep spiking neural network that simulates a biological neural system, the correlation between membrane potential and firing rate is interpreted as an anti-interference index so as to investigate the anti-interference ability of a deep spiking neural network under the regulation of synaptic plasticity in the presence of different amplitudes of an electric field. When the relative variation rate of firing rate is less than 10% or the correlation between the membrane potential is greater than half, the influence of electric field on neural network is relatively small. Otherwise, the influence is relatively large. Simulation results show that: based on the regulation of synaptic plasticity, within a certain electric field interference range, the relative rate of variation of cell firing rates is small compared with non-interference, while correlation between the membrane potential in each layer is large when compared to non-interference.

Key words:  Deep spiking neural network      synaptic plasticity      anti-interference      electric field      firing rate      correlation     
Submitted:  15 December 2018      Accepted:  07 January 2018      Published:  15 November 2018     
*Corresponding Author(s):  Lei Guo     E-mail:  2004008@hebut.edu.cn

Cite this article: 

Lei Guo, Hongyi Shi, Yunge Chen, Hongli Yu. Anti-interference ability of deep spiking neural network. Journal of Integrative Neuroscience, 2018, 17(4): 307-311.

URL: 

https://jin.imrpress.com/EN/10.31083/j.jin.2018.04.0407     OR     https://jin.imrpress.com/EN/Y2018/V17/I4/307

Figure.1.  Pulse time sequence diagrams.

Figure.2.  The firing rate of each layer.

Fig. 3.  Firing rate of output layer neuron.

Fig. 4.  The relative variation rate of firing rate.

Fig. 5.  Correlation between membrane potential of each layer.

Fig. 6.  Correlation between the membrane potential of the output layer neuron and other layers.

Table 1  Correspondences between membrane potential correlations and electric field amplitude
range of electric field amplitude 1~4 5~9 10~13 14~20
range of correlation 0.61~0.71 0.45~0.67 0.26~0.36 0.14~0.24
[1] Zheng-Quan JU, Man MH, Yuan L ( 2012) The design and reliability analysis of the self-organizing fault-tolerant system. Microelectronics & Computer. 29(04), 89-93.
[2] Lin Xh, Wang Xw, Zhang N, Ma HF ( 2015) Supervised learning algorithms for spiking neural networks: a review. Acta Electronica Sinica 43(3), 577-586.
doi: 10.3969/j.issn.0372-2112.2015.03.024
[3] Chen YZ, Xu GZ, Zhou Q, Qu RW, Guo MM, Guo L, Wang XW ( 2014) Construction and simulation of adaptive neural networks based on STDP plasticity. Chinese Journal of Medical Physics 31(02), 4820-4832.
[4] Litwin-Kumar A, Doiron B ( 2014) Formation and maintenance of neuronal assemblies through synaptic plasticity. Nature Communications 5, 5319.
doi: 10.1038/ncomms6319 pmid: 25395015
[5] Wei Y, Koulakov AA ( 2014) Long-term memory stabilized by noise-induced rehearsal. Journal of Neuroscience 34(47), 15804-15815.
doi: 10.1186/1471-2202-14-S1-P220 pmid: 4236406
[6] Yang YP, Ma QS, Xie QM ( 2013) Prediction of electromagnetic interference based on neural network. Journal of Beijing University of Aeronautics and Astronautics 39(5), 697-700, 705.
[7] Yuan L, Mang MH, Chang XL ( 2014) Principle of electromagnetic protection bionics and research on self repairing mechanism of fault. Chinese Engineering Science 16(03), 76-102.
[8] Yu K, Wang J, Deng B, We XL ( 2013) Effects of induced electric field on network synchronization under magnetic stimulation. Journal of Tianjin University: Natural Science and Engineering Technology 46(8), 726-736.
[9] Chang XL, Ding GL, Lou JA ( 2014) Anti disturbance characteristics of synchronous discharge in neural networks. Journal of Shanghai Jiao Tong University 48(10), 1485-1490.
[10] Rich S, Booth V, Zochowski M ( 2015) The role of adaptation current in synchronously firing inhibitory neural networks with various topologies. BMC Neuroscience 16(1), P303.
doi: 10.1186/1471-2202-16-S1-P303 pmid: 4698997
[11] Chen YZ, Xu GZ, Zhou Q, Guo MM, Guo L ( 2015) Research on adaptive neural network anti disturbance ability based on spiking time dependent plasticity. Journal of Biomedical Engineering 39(05), 697-705.
[12] Guo L, Zhang W, Zhang J ( 2018) The effect of an exogenous magnetic field on neural coding in deep spiking neural networks. Journal of Integrative Neuroscience 17(2), 1-12.
doi: 10.3233/JIN-170046
[13] Izhikevich EM ( 2003) Simple model of spiking neurons. IEEE Transactions on Neural Networks 14(6), 1569-1572.
doi: 10.1109/TNN.2003.820440 pmid: 18244602
[14] YU K, Wand J, Deng B, Weu XL ( 2014) Synchronizing characteristics of neural network subject to external electric field. Application Research of Computers 31(1), 70.
[15] Nobukawa S, Nishimura H, Yamanishi T, Liu JQ ( 2015) Chaotic states induced by resetting process in Izhikevich neuron model. Journal of Artificial Intelligence and Soft Computing Research 5(2), 109-119.
[16] Bédard C, Kröger H, Destexhe A ( 2006) Model of low-pass filtering of local field potentials in brain tissue. Physical Review E 73(5), 051911.
doi: 10.1103/PhysRevE.73.051911 pmid: 16802971
[17] Izhikevich EM, Gally JA, Edelman GM ( 2004) Spike-timing dynamics of neuronal groups. Cerebral Cortex 14(8), 933-944.
doi: 10.1093/cercor/bhh053 pmid: 15142958
[18] Zhang ZZ, Han HG ( 2014) Structural design of dynamic feed-forward neural networks based on information entropy. Information and Control 43(2), 181-185.
[19] Radman T, Ramos RL, Brumberg JC, Bikson M ( 2009) Role of cortical cell type and morphology in subthreshold and suprathreshold uniform electric field stimulation in vitro. Brain Stimulation 2(4), 215-228.
doi: 10.1016/j.brs.2009.03.007 pmid: 2797131
[20] Wang ML, Wang JS ( 2015) Excitatory and inhibitory homeostasis of feedback neural circuits based on inhibitory synaptic plasticity. Acta Physica Sinica 64(10), 416-423.
[1] Fatemeh Zareayan Jahromy, Atena Bajoulvand, Mohammad Reza Daliri. Statistical algorithms for emotion classification via functional connectivity[J]. Journal of Integrative Neuroscience, 2019, 18(3): 293-297.
No Suggested Reading articles found!