Spatio-temporal Spike Pattern Classification in Neuromorphic Systems

  • Sadique Sheik
  • Michael Pfeiffer
  • Fabio Stefanini
  • Giacomo Indiveri
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8064)

Abstract

Spike-based neuromorphic electronic architectures offer an attractive solution for implementing compact efficient sensory-motor neural processing systems for robotic applications. Such systems typically comprise event-based sensors and multi-neuron chips that encode, transmit, and process signals using spikes. For robotic applications, the ability to sustain real-time interactions with the environment is an essential requirement. So these neuromorphic systems need to process sensory signals continuously and instantaneously, as the input data arrives, classify the spatio-temporal information contained in the data, and produce appropriate motor outputs in real-time. In this paper we evaluate the computational approaches that have been proposed for classifying spatio-temporal sequences of spike-trains, derive the main principles and the key components that are required to build a neuromorphic system that works in robotic application scenarios, with the constraints imposed by the biologically realistic hardware implementation, and present possible system-level solutions.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Maass, W., Sontag, E.: Neural systems as nonlinear filters. Neural Computation 12(8), 1743–1772 (2000)CrossRefGoogle Scholar
  2. 2.
    Belatreche, A., Maguire, L.P., McGinnity, M.: Advances in design and application of spiking neural networks. Soft Computing 11(3), 239–248 (2006)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Brette, R., Rudolph, M., Carnevale, T., Hines, M., Beeman, D., Bower, J., Diesmann, M., Morrison, A., Goodman, P.H.J.F., Zirpe, M., Natschläger, T., Pecevski, D., Ermentrout, B., Djurfeldt, M., Lansner, A., Rochel, O., Vieville, T., Muller, E., Davison, A., El Boustani, S., Destexhe, A.: Simulation of networks of spiking neurons: A review of tools and strategies. Journal of Computational Neuroscience 23(3), 349–398 (2007)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Liu, S.C., Delbruck, T.: Neuromorphic sensory systems. Current Opinion in Neurobiology 20(3), 288–295 (2010)CrossRefGoogle Scholar
  5. 5.
    Indiveri, G., Linares-Barranco, B., Hamilton, T., van Schaik, A., Etienne-Cummings, R., Delbruck, T., Liu, S.C., Dudek, P., Häfliger, P., Renaud, S., Schemmel, J., Cauwenberghs, G., Arthur, J., Hynna, K., Folowosele, F., Saighi, S., Serrano-Gotarredona, T., Wijekoon, J., Wang, Y., Boahen, K.: Neuromorphic silicon neuron circuits. Frontiers in Neuroscience 5, 1–23 (2011)Google Scholar
  6. 6.
    Choudhary, S., et al.: Silicon neurons that compute. In: Villa, A.E.P., Duch, W., Érdi, P., Masulli, F., Palm, G. (eds.) ICANN 2012, Part I. LNCS, vol. 7552, pp. 121–128. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  7. 7.
    Yu, T., Park, J., Joshi, S., Maier, C., Cauwenberghs, G.: 65k-neuron integrate-and-fire array transceiver with address-event reconfigurable synaptic routing. In: Biomedical Circuits and Systems Conference (BioCAS), pp. 21–24. IEEE (November 2012)Google Scholar
  8. 8.
    Carr, C.E., Konishi, M.: Axonal delay lines for time measurement in the owl’s brainstem. Proceedings of the National Academy of Sciences 85(21), 8311–8315 (1988)CrossRefGoogle Scholar
  9. 9.
    Carr, C.E., Konishi, M.: A circuit for detection of interaural time differences in the brain stem of the barn owl. The Journal of Neuroscience 10(10), 3227–3246 (1990)Google Scholar
  10. 10.
    Pfeiffer, M., Hartbauer, M., Lang, A.B., Maass, W., Römer, H.: Probing real sensory worlds of receivers with unsupervised clustering. PloS One 7(6), e37354 (2012)Google Scholar
  11. 11.
    Johansson, R., Birznieks, I.: First spikes in ensembles of human tactile afferents code complex spatial fingertip events. Nature Neuroscience 7(2), 170–177 (2004)CrossRefGoogle Scholar
  12. 12.
    Singer, W.: Time as coding space? Current Opinion in Neurobiology 9(2), 189–194 (1999)CrossRefGoogle Scholar
  13. 13.
    O’Keefe, J., Burgess, N.: Geometric determinants of the place fields of hippocampal neurons. Nature 381(6581), 425–428 (1996)CrossRefGoogle Scholar
  14. 14.
    Stiefel, K.M., Tapson, J., van Schaik, A.: Temporal order detection and coding in nervous systems. Neural Computation 25(2), 510–531 (2013)CrossRefGoogle Scholar
  15. 15.
    Dhoble, K., Nuntalid, N., Indiveri, G., Kasabov, N.: Online spatio-temporal pattern recognition with evolving spiking neural networks utilising address event representation, rank order, and temporal spike learning. In: International Joint Conference on Neural Networks, IJCNN 2012, pp. 554–560. IEEE (2012)Google Scholar
  16. 16.
    Nessler, B., Pfeiffer, M., Maass, W.: Stdp enables spiking neurons to detect hidden causes of their inputs. In: Bengio, Y., Schuurmans, D., Lafferty, J., Williams, C.I., Culotta, A. (eds.) Advances in Neural Information Processing Systems, vol. 22, pp. 1357–1365 (2009)Google Scholar
  17. 17.
    Masquelier, T., Guyonneau, R., Thorpe, S.J.: Spike timing dependent plasticity finds the start of repeating patterns in continuous spike trains. PLoS One 3(1), e1377 (2008)Google Scholar
  18. 18.
    Gütig, R., Sompolinsky, H.: The tempotron: a neuron that learns spike timing–based decisions. Nature Neuroscience 9, 420–428 (2006)CrossRefGoogle Scholar
  19. 19.
    Thorpe, S., Delorme, A., Van Rullen, R., et al.: Spike-based strategies for rapid processing. Neural Networks 14(6-7), 715–725 (2001)CrossRefGoogle Scholar
  20. 20.
    Legenstein, R., Näger, C., Maass, W.: What can a neuron learn with spike-timing-dependent plasticity? Neural Computation 17(11), 2337–2382 (2005)MathSciNetMATHCrossRefGoogle Scholar
  21. 21.
    Kempter, R., Gerstner, W., Van Hemmen, J.L.: How the threshold of a neuron determines its capacity for coincidence detection. Biosystems 48(1), 105–112 (1998)CrossRefGoogle Scholar
  22. 22.
    Gerstner, W., Kistler, W.: Spiking Neuron Models. In: Single Neurons, Populations, Plasticity. Cambridge University Press (2002)Google Scholar
  23. 23.
    Masquelier, T., Guyonneau, R., Thorpe, S.J.: Competitive stdp-based spike pattern learning. Neural Computation 21(5), 1259–1276 (2009)MATHCrossRefGoogle Scholar
  24. 24.
    Lichtsteiner, P., Posch, C., Delbruck, T.: A 128×128 120dB 30mW asynchronous vision sensor that responds to relative intensity change. In: 2006 IEEE ISSCC Digest of Technical Papers, pp. 508–509. IEEE (February 2006)Google Scholar
  25. 25.
    Nessler, B., Pfeiffer, M., Maass, W.: Bayesian computation emerges in generic cortical microcircuits through spike-timing-dependent plasticity. PLoS Computational Biology (2013)Google Scholar
  26. 26.
    Gütig, R., Sompolinsky, H.: Time-warp-invariant neuronal processing. PLoS Biology 7(7), e1000141 (2009)Google Scholar
  27. 27.
    Koch, C., Poggio, T., Torre, V.: Nonlinear interactions in a dendritic tree: Localization, timing, and role in information processing. Proceedings of the National Academy of Sciences of the USA 80, 2799–2802 (1983)CrossRefGoogle Scholar
  28. 28.
    Wang, Y., Liu, S.C.: Multilayer processing of spatiotemporal spike patterns in a neuron with active dendrites. Neural Computation 8, 2086–2112 (2010)CrossRefGoogle Scholar
  29. 29.
    Arthur, J., Boahen, K.: Recurrently connected silicon neurons with active dendrites for one-shot learning. In: IEEE International Joint Conference on Neural Networks, vol. 3, pp. 1699–1704 (July 2004)Google Scholar
  30. 30.
    Ramakrishnan, S., Wunderlich, R., Hasler, P.: Neuron array with plastic synapses and programmable dendrites. In: Biomedical Circuits and Systems Conference (BioCAS), pp. 400–403. IEEE (November 2012)Google Scholar
  31. 31.
    Rasche, C., Douglas, R.: Forward- and backpropagation in a silicon dendrite. IEEE Transactions on Neural Networks 12, 386–393 (2001)CrossRefGoogle Scholar
  32. 32.
    Mill, R., Sheik, S., Indiveri, G., Denham, S.: A model of stimulus-specific adaptation in neuromorphic aVLSI. In: Biomedical Circuits and Systems Conference (BioCAS), pp. 266–269. IEEE (2010)Google Scholar
  33. 33.
    Buonomano, D.: Decoding temporal information: A model based on short-term synaptic plasticity. The Journal of Neuroscience 20, 1129–1141 (2000)Google Scholar
  34. 34.
    Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation 14(11), 2531–2560 (2002)MATHCrossRefGoogle Scholar
  35. 35.
    Maass, W., Natschläger, T., Markram, H.: Fading memory and kernel properties of generic cortical microcircuit models. Journal of Physiology – Paris 98(4-6), 315–330 (2004)CrossRefGoogle Scholar
  36. 36.
    Sheik, S., Coath, M., Indiveri, G., Denham, S., Wennekers, T., Chicca, E.: Emergent auditory feature tuning in a real-time neuromorphic VLSI system. Frontiers in Neuroscience 6(17) (2012)Google Scholar
  37. 37.
    Coath, M., Mill, R., Denham, S.L., Wennekers, T.: Emergent Feature Sensitivity in a Model of the Auditory Thalamocortical System. Advances in Experimental Medicine and Biology, vol. 718, pp. 7–17. Springer, New York (2011)Google Scholar
  38. 38.
    Izhikevich, E.M.: Polychronization: Computation with spikes. Neural Computation 18(2), 245–282 (2006)MathSciNetMATHCrossRefGoogle Scholar
  39. 39.
    Reichardt, W.: Autocorrelation, a principle for the evaluation of sensory information by the central nervous system. Sensory Communication, 303–317 (1961)Google Scholar
  40. 40.
    Wyss, R., König, P., Verschure, P.F.: Invariant representations of visual patterns in a temporal population code. Proceedings of the National Academy of Sciences 100(1), 324–329 (2003)CrossRefGoogle Scholar
  41. 41.
    Jeffress, L.A.: A place theory of sound localization. J. Comp. Physiol. Psychol. 41(1), 35–39 (1948)CrossRefGoogle Scholar
  42. 42.
    Liu, S.C., Kramer, J., Indiveri, G., Delbruck, T., Douglas, R.: Analog VLSI:Circuits and Principles. MIT Press (2002)Google Scholar
  43. 43.
    Bartolozzi, C., Indiveri, G.: Synaptic dynamics in analog VLSI. Neural Computation 19(10), 2581–2603 (2007)MATHCrossRefGoogle Scholar
  44. 44.
    Bartolozzi, C., Mitra, S., Indiveri, G.: An ultra low power current–mode filter for neuromorphic systems and biomedical signal processing. In: Biomedical Circuits and Systems Conference (BioCAS), pp. 130–133. IEEE (2006)Google Scholar
  45. 45.
    Drakakis, E., Payne, A., Toumazou, C.: “Log-domain state-space”: A systematic transistor-level approach for log-domain filtering. IEEE Transactions on Circuits and Systems II 46(3), 290–305 (1999)CrossRefGoogle Scholar
  46. 46.
    Frey, D.: Log-domain filtering: An approach to current-mode filtering. IEE Proceedings G: Circuits, Devices and Systems 140(6), 406–416 (1993)CrossRefGoogle Scholar
  47. 47.
    Markram, H., Tsodyks, M.: Redistribution of synaptic efficacy between neocortical pyramidal neurons. Nature 382, 807–810 (1996)CrossRefGoogle Scholar
  48. 48.
    Rasche, C., Hahnloser, R.: Silicon synaptic depression. Biological Cybernetics 84(1), 57–62 (2001)CrossRefGoogle Scholar
  49. 49.
    Boegerhausen, M., Suter, P., Liu, S.C.: Modeling short-term synaptic depression in silicon. Neural Computation 15(2), 331–348 (2003)MATHCrossRefGoogle Scholar
  50. 50.
    Varela, J., Sen, K., Gibson, J., Fost, J., Abbott, L., Nelson, S.: A quantitative description of short–term plasticity at excitatory synapses in layer 2/3 of rat primary visual cortex. The Journal of Neuroscience 17, 7926–7940 (1997)Google Scholar
  51. 51.
    Mill, R., Sheik, S., Indiveri, G., Denham, S.: A model of stimulus-specific adaptation in neuromorphic analog VLSI. Transactions on Biomedical Circuits and Systems 5(5), 413–419 (2011)CrossRefGoogle Scholar
  52. 52.
    Basu, A., Ramakrishnan, S., Petre, C., Koziol, S., Brink, S., Hasler, P.: Neural dynamics in reconfigurable silicon. IEEE Transactions on Biomedical Circuits and Systems 4(5), 311–319 (2010)CrossRefGoogle Scholar
  53. 53.
    Sheik, S., Chicca, E., Indiveri, G.: Exploiting device mismatch in neuromorphic VLSI systems to implement axonal delays. In: International Joint Conference on Neural Networks, IJCNN 2012, pp. 1940–1945. IEEE (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Sadique Sheik
    • 1
  • Michael Pfeiffer
    • 1
  • Fabio Stefanini
    • 1
  • Giacomo Indiveri
    • 1
  1. 1.Insitute of NeuroinformaticsUniversity of Zurich and ETH ZurichZurichSwitzerland

Personalised recommendations