Advertisement

Spike Based Information Processing in Spiking Neural Networks

  • Sadique SheikEmail author
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 6)

Abstract

Spiking neural networks are seen as the third generation of neural networks and the closest emulators of their biological counter parts. These networks use spikes as means of transmitting information between neurons. We study the merits and capacity of information transfer using spikes across different encoding and decoding schemes and show that spatio-temporal encoding scheme provides a very high efficiency in information transfer. We then explore learning rules based on neural dynamics that enable learning of spatio-temporal spike patterns. We explore various learning rules that can be used to learn spatio-temporal spike patterns.

Keywords

Learning Rule Rate Code Spike Timing Temporal Code Spike Pattern 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgements

The authors would like to thank Gert Cauwenberghs, Giacomo Indiveri, Elisabetta Chicca and Martin Coath for their invaluable feedback and comments on this manuscript.

References

  1. 1.
    E. Adrian, The Basis of Sensation: The Actions of the Sense Organs (Lowe and Brydone Printers Ltd., London, 1928)Google Scholar
  2. 2.
    A. Borst, M. Egelhaaf, Direction selectivity of blowfly motion-sensitive neurons is computed in a two-stage process. Proc. Natl. Acad. Sci. 87(23), 9363–9367 (1990)CrossRefGoogle Scholar
  3. 3.
    N. Brunel, J.P. Nadal, G. Toulouse, Information capacity of a perceptron. J. Phys. A: Math. General 25(19), 5017 (1992). http://stacks.iop.org/0305-4470/25/i=19/a=015
  4. 4.
    C. Carr, M. Konishi, Axonal delay lines for time measurement in the owl’s brainstem. Proc. Natl. Acad. Sci. 85(21), 8311–8315 (1988)CrossRefGoogle Scholar
  5. 5.
    C. Carr, M. Konishi, A circuit for detection of interaural time differences in the brain stem of the barn owl. J. Neurosci. 10(10), 3227–3246 (1990)Google Scholar
  6. 6.
    A. Dempster, N. Laird, D. Rubin, Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B (Methodological) 1–38 (1977)Google Scholar
  7. 7.
    R. Florian, Tempotron-like learning with resume, in Artificial Neural Networks-ICANN 2008 (Springer, 2008), pp. 368–375Google Scholar
  8. 8.
    R. Florian, The chronotron: a neuron that learns to fire temporally precise spike patterns. PLoS ONE 7(8), e40,233 (2012)Google Scholar
  9. 9.
    E. Gardner, The space of interactions in neural network models. J. Phys. A: Math. Gen. 21(1), 257 (1988)MathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    R. Gütig, H. Sompolinsky, The tempotron: a neuron that learns spike timing-based decisions. Nat. Neurosci. 9, 420–428 (2006). doi: 10.1038/nn1643 CrossRefGoogle Scholar
  11. 11.
    S. Hussain, A. Basu, M. Wang, T. Hamilton, Deltron: neuromorphic architectures for delay based learning, in 2012 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS) (2012), pp. 304–307. doi: 10.1109/APCCAS.2012.6419032
  12. 12.
    E. Izhikevich, Polychronization: computation with spikes. Neural Comput. 18(2), 245–282 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    R. Johansson, I. Birznieks, First spikes in ensembles of human tactile afferents code complex spatial fingertip events. Nature Neurosci. 7(2), 170–177 (2004)CrossRefGoogle Scholar
  14. 14.
    R. Kempter, W. Gerstner, J.V. Hemmen, How the threshold of a neuron determines its capacity for coincidence detection. Biosystems 48(1), 105–112 (1998)CrossRefGoogle Scholar
  15. 15.
    P. Knüsel, R. Wyss, P. König, P.F. Verschure, Decoding a temporal population code. Neural Comput. 16(10), 2079–2100 (2004)CrossRefzbMATHGoogle Scholar
  16. 16.
    R. Legenstein, C. Näger, W. Maass, What can a neuron learn with spike-timing-dependent plasticity? Neural Comput. 17(11), 2337–2382 (2005)MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    T. Masquelier, R. Guyonneau, S. Thorpe, Spike timing dependent plasticity finds the start of repeating patterns in continuous spike trains. PLoS ONE 3(1), e1377 (2008). doi: 10.1371/journal.pone.0001377 CrossRefGoogle Scholar
  18. 18.
    T. Masquelier, R. Guyonneau, S. Thorpe, Competitive STDP-based spike pattern learning. Neural Comput. 21(5), 1259–1276 (2009). doi: 10.1162/neco.2008.06-08-804 CrossRefzbMATHGoogle Scholar
  19. 19.
    M. Minsky, S. Papert, Perceptrons: An Introduction to Computational Geometry (MIT Press, Cambridge, Mass, 1969)zbMATHGoogle Scholar
  20. 20.
    A. Mohemmed, S. Schliebs, S. Matsuda, N. Kasabov, Span: spike pattern association neuron for learning spatio-temporal spike patterns. Int. J. Neural Syst. 22(04) (2012)Google Scholar
  21. 21.
    T. Natschläger, W. Maass, H. Markram, The “liquid computer”: a novel strategy for real-time computing on time series. Spec. Issue Found. Inf. Process. TELEMATIK 8(1), 39–43 (2002)Google Scholar
  22. 22.
    B. Nessler, M. Pfeiffer, W. Maass, STDP enables spiking neurons to detect hidden causes of their inputs, in Advances in Neural Information Processing Systems, vol. 22, ed. by Y. Bengio, D. Schuurmans, J. Lafferty, C.I. Williams, A. Culotta (2009), pp. 1357–1365Google Scholar
  23. 23.
    J. O’Keefe, N. Burgess, Geometric determinants of the place fields of hippocampal neurons. Nature 381(6581), 425–428 (1996)CrossRefGoogle Scholar
  24. 24.
    M. Pfeiffer, M. Hartbauer, A. Lang, W. Maass, H. Römer, Probing real sensory worlds of receivers with unsupervised clustering. PLoS ONE 7(6), e37,354 (2012)Google Scholar
  25. 25.
    F. Ponulak, A. Kasiński, Supervised learning in spiking neural networks with resume: sequence learning, classification, and spike shifting. Neural Comput. 22(2), 467–510 (2010)MathSciNetCrossRefzbMATHGoogle Scholar
  26. 26.
    F. Rieke, Spikes: Reading the Neural Code (The MIT Press, 1997)Google Scholar
  27. 27.
    F. Rosenblatt, The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65(6), 386–408 (1958). doi: 10.1037/h0042519 CrossRefGoogle Scholar
  28. 28.
    M. van Rossum, A novel spike distance. Neural Comput. 13(4), 751–763 (2001)CrossRefzbMATHGoogle Scholar
  29. 29.
    S. Sheik, Autonomous learning in neuromorphic systems for recognition of spatio-temporal spike patterns. Ph.D. thesis, ETH-Zürich (2013)Google Scholar
  30. 30.
    S. Sheik, S. Paul, C. Augustine, G. Cauwenberghs, Membrane-dependent neuromorphic learning rule for unsupervised spike pattern detection, in Biomedical Circuits and Systems Conference (BioCAS), 2016 (IEEE, 2016)Google Scholar
  31. 31.
    W. Singer, Time as coding space? Curr. Opin. Neurobiol. 9(2), 189–194 (1999)CrossRefGoogle Scholar
  32. 32.
    K. Stiefel, J. Tapson, A. van Schaik, Temporal order detection and coding in nervous systems. Neural Comput. 25(2), 510–531 (2013)CrossRefzbMATHGoogle Scholar
  33. 33.
    S. Thorpe, A. Delorme, R.V. Rullen et al., Spike-based strategies for rapid processing. Neural Netw. 14(6–7), 715–725 (2001)CrossRefGoogle Scholar
  34. 34.
    J. Victor, K. Purpura, Metric-space analysis of spike trains: theory, algorithms and application. Netw.: Comput. Neural Syst. 8(2), 127–164 (1997)CrossRefzbMATHGoogle Scholar
  35. 35.
    J. Vreeken, Spiking neural networks, an introduction. Technical Report UU-CS (2003-008), 1–5 (2003)Google Scholar
  36. 36.
    B. Widrow, M. Hoff, Adaptive switching circuits, in 1960 IRE WESCON convention record, Part 4 (IRE, New York, 1960), pp. 96–104. http://isl-www.stanford.edu/~widrow/papers/c1960adaptiveswitching.pdf
  37. 37.
    R. Wyss, P. König, P. Verschure, Invariant representations of visual patterns in a temporal population code. Proc. Natl. Acad. Sci. 100(1), 324–329 (2003)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.BioCircuits Institute, UCSDSan DiegoUSA

Personalised recommendations