Skip to main content

Advertisement

SpringerLink
Log in

Function approximation by hardware spiking neural network

  • Published:
Journal of Computational Electronics Aims and scope Submit manuscript

Abstract

Spiking neural networks (SNN) represent a special class of artificial neural networks, where neu-ron models communicate by sequences of spikes. SNNs are often referred to as the third generation of neural networks that highly inspired from natural computing in the brain and recent advances in neuroscience. In this paper we implement biologically-inspired, hardware-realizable SNN architecture using integrate-and-fire units, which is capable of approximating a real-valued function. Based on the results of MATLAB simulations, hardware synthesis and FPGA implementation, it is demonstrated that the implemented hardware can approximate linear and nonlinear functions with low minimum relative error. This framework may represent a fundamental computational unit for the development of artificial SNN, opening new perspectives in pattern recognition tasks.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice Hall, New Jersey (1998)

    Google Scholar 

  2. Maass, W.: Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10(9), 1659–1671 (1997)

    Article  Google Scholar 

  3. Thorpe, S., Fize, D., Marlot, C.: Speed of processing in the human visual system. Nature 381(6582), 520–522 (1996)

    Article  Google Scholar 

  4. De Garis, H., Shuo, C., Goertzel, B., Ruiting, L.: A world survey of artificial brain projects. Part I: large-scale brain simulations. Neurocomputing 74(1), 3–29 (2010)

    Article  Google Scholar 

  5. Shayani, H., Bentley, P., Tyrrell, A.M.: A cellular structure for online routing of digital spiking neuron axons and dendrites on FPGAs. In: Evolvable Systems: From Biology to Hardware, pp. 273–284. Springer, Berlin (2008)

  6. Thomas, D.B., Luk, W.: FPGA accelerated simulation of biologically plausible spiking neural networks. In: 17th IEEE Symposium on Field Programmable Custom Computing Machines, 2009 (FCCM’09) pp. 45–52. (2009)

  7. Trappenberg, T.: Fundamentals of Computational Neuroscience. Oxford University Press, Oxford (2010)

    MATH  Google Scholar 

  8. Wade, J.: A biologically inspired training algorithm for spiking neural networks. Ph.D. Thesis, University of Ulster (2010)

  9. Paugam-Moisy, H., Bohte, S.: Computing with spiking neuron networks. In: Handbook of Natural Computing, p. 40. Springer, Heidelberg (2009)

  10. Shadlen, M.N., Newsome, W.T.: Noise, neural codes and cortical organization. Curr. Opin. Neurobiol. 4(4), 569–579 (1994)

    Article  Google Scholar 

  11. Rieke, F., Warland, D., de Ruyter van Steveninck, R., Bialek, W.: Spikes, Exploring the Neural Code. The MIT Press, Cambridge (1996)

    MATH  Google Scholar 

  12. Gerstein, G.L., Mandelbrot, B.: Random walk models for the spike activity of a single neuron. Biophys. J. 4, 41–68 (1964)

    Article  Google Scholar 

  13. Thorpe, S., Fabre-Thorpe, M.: Seeking categories in the brain. Science 291, 260–263 (2001)

    Article  Google Scholar 

  14. Touboul, J., Brette, R.: Dynamics and bifurcations of the adaptive exponential integrate-and-fire model. Biol. Cybern. 99(4–5), 319–334 (2008)

    Article  MathSciNet  MATH  Google Scholar 

  15. Cessac, B., Viéville, T.: On dynamics of integrate-and-fire neural networks with adaptive conductances. Front. Neurosci. 2(2) (2008)

  16. Gray, C.M., Singer, W.: Stimulus specific neuronal oscillations in orientation columns of cat visual cortex. Proc. Natl. Acad. Sci. U.S.A. 86, 1698–1702 (1989)

    Article  Google Scholar 

  17. Maass, W.: Motivation, theory, and applications of liquid state machines. In: Cooper, B., Sorbi, A. (eds.) Computability in Context: Computation and Logic in the Real World. Imperial College Press, London (2009)

    Google Scholar 

  18. Verstraeten, D., Schrauwen, B., d’Haene, M., Stroobandt, D.: An experimental unification of reservoir computing methods. Neural Netw. 20(3), 391–403 (2007)

    Article  MATH  Google Scholar 

  19. Brette, R., Goodman, D.F.: Simulating spiking neural networks on GPU. Network 23(4), 167–182 (2012)

    Google Scholar 

  20. Izhikevich, E.M.: Simple model of spiking neurons. IEEE Trans. Neural Netw. 14(6), 1569–1572 (2003)

    Article  MathSciNet  Google Scholar 

  21. Izhikevich, E.M.: Which model to use for cortical spiking neurons? IEEE Trans. Neural Netw. 15(5), 1063–1070 (2004)

    Article  Google Scholar 

  22. Iannella, N., Back, A.D.: A spiking neural network architecture for nonlinear function approximation. Neural Netw. 14(6), 933–939 (2001)

    Article  Google Scholar 

  23. Vato, A., Semprini, M., Maggiolini, E., Szymanski, F.D., Fadiga, L., Panzeri, S., Mussa-Ivaldi, F.A.: Shaping the dynamics of a bidirectional neural interface. PLoS Comput. Biol. 8(7), e1002578 (2012)

    Article  Google Scholar 

  24. Kestur, S., Park, M. S., Sabarad, J., Dantara, D., Narayanan, V., Chen, Y., Khosla, D.: Emulating mammalian vision on reconfigurable hardware. In 2012 IEEE 20th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp. 141–148. (2012)

  25. Courtine, G., Micera, S., DiGiovanna, J., del R Millán, J.: Brain-machine interface: closer to therapeutic reality? Lancet 381(9866), 515–517 (2013)

    Article  Google Scholar 

  26. Vato, A., Szymanski, F.D., Semprini, M., Mussa-Ivaldi, F.A., Panzeri, S.: A bidirectional brain-machine interface algorithm that approximates arbitrary force-fields. PloS One 9(3), e91677 (2014)

    Article  Google Scholar 

  27. Nazari, S., Faez, K., Amiri, M., Karami, E.: A novel digital implementation of neuron-astrocyte interactions. J. Comput. Electron., 1–13 (2014)

  28. Nazari, S., Amiri, M., Amiri, M.: Multiplier-less digital implementation of neuron-astrocyte Signalling on FPGA. Neurocomputing (2015)

  29. Li, W.X., Cheung, R.C., Chan, R.H., Song, D., Berger, T.W.: Real-time prediction of neuronal population spiking activity using FPGA. IEEE Trans. Biomed. Circuits Syst. 7(4), 489–498 (2013)

    Article  Google Scholar 

  30. Maxfield, C.: The Design Warrior’s Guide to FPGAs: Devices, Tools and Flows. Elsevier, Boston (2004)

    Google Scholar 

  31. Kuon, I., Tessier, R., Rose, J.: Fpga architecture: survey and challenges. Found. Trends Electron. Des. Autom. 2(2), 135–253 (2008)

    Article  Google Scholar 

  32. Kilts, S.: Advanced FPGA Design: Architecture, Implementation, and Optimization. Wiley, New YorK (2007)

    Book  Google Scholar 

  33. Azghadi Rahimi, M., Al-Sarawi, S., Abbott, D., Lannella, N.: A neuromorphic VLSI design for spike timing and rate based synaptic plasticity. Neural Netw. 45, 70–82 (2013)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Electronic, College of Engineering, Kermanshah Science and Research Branch, Islamic Azad University, Kermanshah, Iran

    Edris Zaman Farsa

  2. Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran

    Soheila Nazari

  3. Department of Electrical Engineering, Razi University, Kermanshah, Iran

    Morteza Gholami

Authors
  1. Edris Zaman Farsa
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Soheila Nazari
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Morteza Gholami
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Edris Zaman Farsa.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zaman Farsa, E., Nazari, S. & Gholami, M. Function approximation by hardware spiking neural network. J Comput Electron 14, 707–716 (2015). https://doi.org/10.1007/s10825-015-0709-x

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10825-015-0709-x

Keywords

Search

Navigation