Computation by Time

Abstract

Over the last years, the amount of research performed in the field of spiking neural networks has been growing steadily. Spiking neurons are modeled to approximate the complex dynamic behavior of biological neurons. They communicate via discrete impulses called spikes with the actual information being encoded in the timing of these spikes. As already pointed out by Maass in his paper on the third generation of neural network models, this renders time a central factor for neural computation. In this paper, we investigate at different levels of granularity how absolute time and relative timing enable new ways of biologically inspired neural information processing. At the lowest level of single spiking neurons, we give an overview of coding schemes and learning techniques which rely on precisely timed neural spikes. A high-level perspective is provided in the second part of the paper which focuses on the role of time at the network level. The third aspect of time considered in this work is related to the interfacing of neural networks with real-time systems. In this context, we discuss how the concepts of computation by time can be implemented in computer simulations and on specialized neuromorphic hardware. The contributions of this paper are twofold: first, we show how the exact modeling of time in spiking neural networks serves as an important basis for powerful computation based on neurobiological principles. Second, by presenting a range of diverse learning techniques, we prove the biologically plausible applicability of spiking neural networks to real world problems like pattern recognition and path planning.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Notes

  1. 1.

    Note that although \(L^M\) is usually implemented as a spiking neural network, the theory of LSMs allows arbitrary implementations as long as they meet a set of formal mathematical requirements.

References

  1. 1.

    Benjamin BV, Peiran Gao, McQuinn E, Choudhary S, Chandrasekaran AR, Bussat JM, Alvarez-Icaza R, Arthur JV, Merolla PA, Boahen K (2014) Neurogrid: a mixed-analog-digital multichip system for large-scale neural simulations. Proc IEEE 102(5):699–716

    Article  Google Scholar 

  2. 2.

    Bi G, Poo M (2001) Synaptic modification by correlated activity: Hebb’s postulate revisited. Annu Rev Neurosci 24(1):139–166

    Article  Google Scholar 

  3. 3.

    Bohte SM (2004) The evidence for neural information processing with precise spike-times: a survey: natural computing. Nat Comput 3(2):195–206

    MathSciNet  Article  MATH  Google Scholar 

  4. 4.

    Bohte SM, Kok JN, La Poutré H (2002) Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48(1–4):17–37

    Article  MATH  Google Scholar 

  5. 5.

    Bohte SM, La Poutre H, Kok JN (2002) Unsupervised clustering with spiking neurons by sparse temporal coding and multilayer RBF networks. Neural Netw IEEE Trans 13(2):426–435

    Article  Google Scholar 

  6. 6.

    Brea J, Senn W, Pfister JP (2013) Matching recall and storage in sequence learning with spiking neural networks. J Neurosci 33(23):9565–9575

    Article  Google Scholar 

  7. 7.

    Brunel N (2000) Dynamics of sparsely connected networks of excitatory and inhibitory spiking neurons. J Comput Neurosci 8(3):183–208

    Article  MATH  Google Scholar 

  8. 8.

    Carnell A, Richardson D (2005) Linear algebra for time series of spikes. In: Proceedings of ESANN, pp 363–368

  9. 9.

    Carnevale N, Hines M (2015) NEURON for empirically-based simulations of neurons and networks of neurons: project homepage. http://www.neuron.yale.edu/neuron/

  10. 10.

    Cyr A, Boukadoum M, Thériault F (2014) Operant conditioning: a minimal components requirement in artificial spiking neurons designed for bio-inspired Robot’s controller. Front Neurorobot 8(21)

  11. 11.

    Diamond MC (2001) Response of the brain to enrichment. Anais da Academia Brasileira de Ciências 73:211–220

    Article  Google Scholar 

  12. 12.

    Farries MA, Fairhall AL (2007) Reinforcement learning with modulated spike timing-dependent synaptic plasticity. J Neurophys 98(6):3648–3665

    Article  Google Scholar 

  13. 13.

    Floreano D, Mattiussi C (2001) Evolution of spiking neural controllers for autonomous vision-based robots. In: Goos G, Hartmanis J, van Leeuwen J, Gomi T (eds) Evolutionary robotics, vol 2217., From intelligent robotics to artificial life, lecture notes in computer scienceSpringer, Berlin, pp 38–61

    Google Scholar 

  14. 14.

    Florian RV (2005) A reinforcement learning algorithm for spiking neural networks. In: Proceedings of the seventh international symposium on symbolic and numeric algorithms for scientific computing, SYNASC ’05. IEEE Computer Society, Washington, DC, USA

  15. 15.

    Frémaux N, Sprekeler H, Gerstner W (2013) Reinforcement learning using a continuous time actor-critic framework with spiking neurons. PLoS Comput Biol 9(4):e1003,024

    MathSciNet  Article  Google Scholar 

  16. 16.

    Furber S, Brown A (2009) Biologically-inspired massively-parallel architectures - computing beyond a million processors. In: Application of concurrency to system design, 2009 (ACSD ’09). Ninth international conference on, pp 3–12

  17. 17.

    Furber SB, Lester DR, Plana LA, Garside JD, Painkras E, Temple S, Brown AD (2013) Overview of the spinnaker system architecture. Comput IEEE Trans 62(12):2454–2467

    MathSciNet  Article  Google Scholar 

  18. 18.

    Gerstner W, Kempter R, van Hemmen JL, Wagner H (1996) A neuronal learning rule for sub-millisecond temporal coding. Nature 383(6595):76–78

    Article  Google Scholar 

  19. 19.

    Gerstner W, Kistler WM (2002) Spiking neuron models: single neurons, populations, plasticity. Cambridge University Press, Cambridge

    Book  MATH  Google Scholar 

  20. 20.

    Gewaltig MO, Morrison A, Plesser HE (2012) NEST by example: an introduction to the neural simulation tool NEST. In: Le Novère N (ed) Computational systems neurobiology. Springer, The Netherlands, pp 533–558

    Chapter  Google Scholar 

  21. 21.

    Goodman Dan FM, Brette R (2009) The brian simulator. Front Neurosci 3(2):192

    Article  Google Scholar 

  22. 22.

    Grüning A, Bohte SM (2014) Spiking neural networks: principles and challenges. In: ESANN 2014. 22nd European symposium on artificial neural networks, computational intelligence and machine learning. Bruges, April 23–25, 2014. i6doc.com, Louvain-La-Neuve

  23. 23.

    Gütig R (2014) To spike, or when to spike? Theor Comput Neurosci 25:134–139

    Google Scholar 

  24. 24.

    Gütig R, Sompolinsky H (2006) The tempotron: a neuron that learns spike timing-based decisions. Nat Neurosci 9(3):420–428

    Article  Google Scholar 

  25. 25.

    Hebb DO (1949) The organization of behavior: a neuropsychological theory. Wiley, New York

    Google Scholar 

  26. 26.

    Hihi SE, Bengio Y (1996) Hierarchical recurrent neural networks for long-term dependencies. In: Touretzky DS, Mozer MC, Hasselmo ME (eds) Advances in neural information processing systems 8. MIT Press, Cambridge, pp 493–499

    Google Scholar 

  27. 27.

    Hodgkin AL, Huxley AF (1952) A quantitative description of membrane current and its application to conduction and excitation in nerve. J Physiol 117(4):500–544

    Article  Google Scholar 

  28. 28.

    Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4(2):251–257

    Article  Google Scholar 

  29. 29.

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

    MathSciNet  Article  Google Scholar 

  30. 30.

    Izhikevich EM (2007) Solving the distal reward problem through linkage of STDP and dopamine signaling. Cereb Cortex 17(10):2443–2452

    Article  Google Scholar 

  31. 31.

    Jin X, Lujan M, Plana LA, Davies S, Temple S, Furber SB (2010) Modeling spiking neural networks on spinnaker. Comput Sci Eng 12(5):91–97

    Article  Google Scholar 

  32. 32.

    Jin X, Rast A, Galluppi F, Khan M, Furber S (2009) Implementing learning on the spinnaker universal neural chip multiprocessor. In: Leung C, Lee M, Chan J (eds) Neural information processing, vol 5863., Lecture notes in computer scienceSpringer, Berlin, pp 425–432

    Chapter  Google Scholar 

  33. 33.

    Kandel ER, Siegelbaum SA (2013) Cellular mechanisms of implicit memory storage and the biological basis of individuality. In: Kandel ER, Schwartz JH, Jessel TM, Siegelbaum SA, Hudspeth AJ (eds) Principles of neural science. McGraw-Hill, New York, pp 1461–1486

    Google Scholar 

  34. 34.

    Kandel ER, Siegelbaum SA (2013) Synaptic integration in the central nervous system. In: Kandel ER, Schwartz JH, Jessel TM, Siegelbaum SA, Hudspeth AJ (eds) Principles of neural science. McGraw-Hill, New York, pp 210–235

    Google Scholar 

  35. 35.

    Koester J, Siegelbaum SA (2013) Propagated signaling: the action potential. In: Kandel ER, Schwartz JH, Jessel TM, Siegelbaum SA, Hudspeth AJ (eds) Principles of neural science. McGraw-Hill, New York, pp 148–176

    Google Scholar 

  36. 36.

    Krichmar J (2008) Neurorobotics. Scholarpedia 3(3):1365

    Article  Google Scholar 

  37. 37.

    Krichmar J (2015) CARLsim: GPU-accelerated spiking neural network simulator: project homepage. http://www.socsci.uci.edu/~jkrichma/CARLsim/index.html

  38. 38.

    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444

    Article  Google Scholar 

  39. 39.

    Legenstein R, Naeger C, Maass W (2005) What can a neuron learn with spike-timing-dependent plasticity? Neural Comput 17(11):2337–2382

    MathSciNet  Article  MATH  Google Scholar 

  40. 40.

    Legenstein R, Pecevski D, Maass W (2008) A learning theory for reward-modulated spike-timing-dependent plasticity with application to biofeedback. PLoS Comput Biol 4(10):e1000,180

    MathSciNet  Article  Google Scholar 

  41. 41.

    Lukoševičius M, Jaeger H (2009) Reservoir computing approaches to recurrent neural network training. Comput Sci Rev 3(3):127–149

    Article  MATH  Google Scholar 

  42. 42.

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

    Article  Google Scholar 

  43. 43.

    Maass W, Jaeger H, Steil J, Dominey PF, Schrauwen B (2015) Web portal for reservoir computing. http://organic.elis.ugent.be/

  44. 44.

    Maass W, Natschläger T, Markram H (2002) Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput 14(11):2531–2560

    Article  MATH  Google Scholar 

  45. 45.

    Markram H, Lübke J, Frotscher M, Sakmann B (1997) Regulation of synaptic efficacy by coincidence of postsynaptic APs and EPSPs. Science 275(5297):213–215

    Article  Google Scholar 

  46. 46.

    Masquelier T, Thorpe SJ (2007) Unsupervised learning of visual features through spike timing dependent plasticity. PLoS Comput Biol 3(2):e31

    Article  Google Scholar 

  47. 47.

    McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5(4):115–133

    MathSciNet  Article  MATH  Google Scholar 

  48. 48.

    Memmesheimer RM, Rubin R, Ölveczky BP, Sompolinsky H (2014) Learning precisely timed spikes. Neuron 82(4):925–938

    Article  Google Scholar 

  49. 49.

    Morrison A, Diesmann M, Gerstner W (2008) Phenomenological models of synaptic plasticity based on spike timing. Biol Cybern 98(6):459–478

    MathSciNet  Article  MATH  Google Scholar 

  50. 50.

    Natschläger T, Ruf B (1998) Spatial and temporal pattern analysis via spiking neurons. Network 9(3):319–332

    Article  MATH  Google Scholar 

  51. 51.

    NEST Initiative (2015) NEST: project homepage. http://www.nest-initiative.org/

  52. 52.

    Nichols C, McDaid LJ, Siddique NH (2010) Case study on a self-organizing spiking neural network for robot navigation. Int J Neural Syst 20(06):501–508

    Article  Google Scholar 

  53. 53.

    Norton D, Ventura D (2006) Preparing more effective liquid state machines using hebbian learning. In: Neural networks, 2006. IJCNN ’06. International joint conference on, pp 4243–4248

  54. 54.

    Pfister JP (2006) Triplets of spikes in a model of spike timing-dependent plasticity. J Neurosci 26(38):9673–9682

    Article  Google Scholar 

  55. 55.

    Ponulak F, Hopfield JJ (2013) Rapid, parallel path planning by propagating wavefronts of spiking neural activity. Front Comput Neurosci 7:98

    Article  Google Scholar 

  56. 56.

    Ponulak F, Kasiński A (2009) Supervised learning in spiking neural networks with ReSuMe: sequence learning, classification, and spike shifting. Neural Comput 22(2):467–510

    MathSciNet  Article  MATH  Google Scholar 

  57. 57.

    Ponulak F, Kasinski A (2011) Introduction to spiking neural networks: information processing, learning and applications. Acta Neurobiol Exp 71(4):409–433

    Google Scholar 

  58. 58.

    Ros E, Carrillo R, Ortigosa EM, Barbour B, Agís R (2006) Event-driven simulation scheme for spiking neural networks using lookup tables to characterize neuronal dynamics. Neural Comput 18(12):2959–2993

    Article  MATH  Google Scholar 

  59. 59.

    Rosenblatt F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65(6):386–408

    MathSciNet  Article  Google Scholar 

  60. 60.

    Schemmel J, Brüderle D, Grübl A, Hock M, Meier K, Millner S (2010) A wafer-scale neuromorphic hardware system for large-scale neural modeling. In: Circuits and systems (ISCAS), proceedings of 2010 IEEE international symposium on, pp 1947–1950

  61. 61.

    Schemmel J, Grubl A, Hartmann S, Kononov A, Mayr C, Meier K, Millner S, Partzsch J, Schiefer S, Scholze S, Schuffny R, Schwartz M (2012) Live demonstration: a scaled-down version of the BrainScaleS wafer-scale neuromorphic system. In: Circuits and systems (ISCAS), 2012 IEEE international symposium on, p 702

  62. 62.

    Schliebs S, Kasabov N (2014) Computational modeling with spiking neural networks. In: Kasabov N (ed) Springer handbook of bio-/neuroinformatics. Springer, Berlin, pp 625–646

    Chapter  Google Scholar 

  63. 63.

    Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117

    Article  Google Scholar 

  64. 64.

    Senn W, Pfister JP (2014) Reinforcement learning in cortical networks. In: Jaeger D, Jung R (eds) Encyclopedia of computational neuroscience. Springer, New York, pp 1–9

    Google Scholar 

  65. 65.

    Sjöström PJ, Turrigiano GG, Nelson SB (2001) Rate, timing, and cooperativity jointly determine cortical synaptic plasticity. Neuron 32(6):1149–1164

    Article  Google Scholar 

  66. 66.

    Sporea I, Grüning A (2012) Supervised learning in multilayer spiking neural networks. Neural Comput 25(2):473–509

    MathSciNet  Article  MATH  Google Scholar 

  67. 67.

    Sutton RS, Precup D, Singh S (1999) Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif Intell 112(1–2):181–211

    MathSciNet  Article  MATH  Google Scholar 

  68. 68.

    Tani J (2014) Self-organization and compositionality in cognitive brains: a neurorobotics study. Proc IEEE 102(4):586–605

    Article  Google Scholar 

  69. 69.

    The Human Brain Project (2015) Project homepage. https://www.humanbrainproject.eu

  70. 70.

    Walter F, Röhrbein F, Knoll A (2015) Neuromorphic implementations of neurobiological learning algorithms for spiking neural networks. Neural Netw

  71. 71.

    Werbos PJ (1990) Backpropagation through time: what it does and how to do it. Proc IEEE 78(10):1550–1560

    Article  Google Scholar 

  72. 72.

    Wysoski S, Benuskova L, Kasabov N (2006) On-line learning with structural adaptation in a network of spiking neurons for visual pattern recognition. In: Kollias S, Stafylopatis A, Duch W, Oja E (eds) Artificial neural networks—ICANN 2006, vol 4131., Lecture notes in computer scienceSpringer, Berlin, pp 61–70

    Chapter  Google Scholar 

  73. 73.

    Xu Y, Zeng X, Zhong S (2013) A new supervised learning algorithm for spiking neurons. Neural Comput 25(6):1472–1511

    MathSciNet  Article  Google Scholar 

Download references

Acknowledgments

The research leading to these results has received funding from the European Union Seventh Framework Programme (FP7/2007–2013) under grant agreement no 604102 (HBP).

Author information

Affiliations

Authors

Corresponding author

Correspondence to Florian Walter.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Walter, F., Röhrbein, F. & Knoll, A. Computation by Time. Neural Process Lett 44, 103–124 (2016). https://doi.org/10.1007/s11063-015-9478-6

Download citation

Keywords

  • Spiking neural network
  • Neurobiological learning
  • Reservoir computing
  • Hierarchical learning
  • Neural coding
  • Neuromorphic hardware