Skip to main content

Memory Trace in Spiking Neural Networks

  • Conference paper
  • 5701 Accesses

Part of the Lecture Notes in Computer Science book series (LNTCS,volume 8131)

Abstract

Spiking neural networks have a limited memory capacity, such that a stimulus arriving at time t would vanish over a timescale of 200-300 milliseconds [1]. Therefore, only neural computations that require history dependencies within this short range can be accomplished. In this paper, the limited memory capacity of a spiking neural network is extended by coupling it to an delayed-dynamical system. This presents the possibility of information exchange between spiking neurons and continuous delayed systems.

Keywords

  • spiking neural networks
  • memory trace
  • delayed-dynamical systems
  • reservoir computing

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-642-40728-4_33
  • Chapter length: 8 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   79.99
Price excludes VAT (USA)
  • ISBN: 978-3-642-40728-4
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   99.99
Price excludes VAT (USA)

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Maass, W., Natschläger, T., Markram, H.: Fading memory and kernel properties of generic cortical microcircuit models. Journal of Physiology 98, 315–330 (2004)

    Google Scholar 

  2. Buonomano, D.V., Maass, W.: State-dependent computations: spatiotemporal processing in cortical networks. Nature Reviews Neuroscience 10, 113–125 (2009)

    CrossRef  Google Scholar 

  3. Durstewitz, D., Seamans, J.K., Sejnowski, T.J.: Neurocomputational models of working memory. Nature Neuroscience 3(suppl.), 1184–1191 (2000)

    CrossRef  Google Scholar 

  4. Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Computation 14, 2531–2560 (2002)

    CrossRef  MATH  Google Scholar 

  5. Jäger, H.: The echo state approach to analysing and training recurrent neural networks. GMD Report 147 (2001)

    Google Scholar 

  6. Mayor, J., Gerstner, W.: Signal buffering in random networks of spiking neurons: Microscopic versus macroscopic phenomena. Physical Review E 72, 15 (2005)

    MathSciNet  CrossRef  Google Scholar 

  7. Körding, K.P., Wolpert, D.M.: Bayesian integration in sensorimotor learning. Nature 427, 244–247 (2004)

    CrossRef  Google Scholar 

  8. Churchland, M.M., et al.: Neural population dynamics during reaching. Nature 487, 51–56 (2012)

    Google Scholar 

  9. Maass, W., Joshi, P., Sontag, E.D.: Computational aspects of feedback in neural circuits. PLoS Comput. Biol. 3, e165 (2007)

    Google Scholar 

  10. Pascanu, R., Jäger, H.: A Neurodynamical Model for Working Memory. Neural Networks 1, 123 (2010)

    Google Scholar 

  11. Forde, J.E.: Delay Differential Equation Models in Mathematical Biology. PhD Thesis

    Google Scholar 

  12. Natschläger, T., Markram, H., Maass, W.: Computer Models and Analysis Tools for Neural Microcircuits. Neuro- Science Databases. A Practical Guide, 121–136 (2003)

    Google Scholar 

  13. Mackey, M.C., Glass, L.: Oscillation and Chaos in Phisiological Control Systems. Science (1977)

    Google Scholar 

  14. Appeltant, L., et al.: Information processing using a single dynamical node as complex system. Nature Communications 2, 468 (2011)

    CrossRef  Google Scholar 

  15. Ganguli, S., Huh, D., Sompolinsky, H.: Memory traces in dynamical systems. PNAS 105, 18970–18975 (2008)

    CrossRef  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2013 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Castellano, M., Pipa, G. (2013). Memory Trace in Spiking Neural Networks. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds) Artificial Neural Networks and Machine Learning – ICANN 2013. ICANN 2013. Lecture Notes in Computer Science, vol 8131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40728-4_33

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-40728-4_33

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-40727-7

  • Online ISBN: 978-3-642-40728-4

  • eBook Packages: Computer ScienceComputer Science (R0)