Advertisement

The Importance of Self-excitation in Spiking Neural Networks Evolved to Recognize Temporal Patterns

  • Muhammad Yaqoob
  • Volker Steuber
  • Borys WróbelEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11727)

Abstract

Biological and artificial spiking neural networks process information by changing their states in response to the temporal patterns of input and of the activity of the network itself. Here we analyse very small networks, evolved to recognize three signals in a specific pattern (ABC) in a continuous temporal stream of signals (...CABCACB...). This task can be accomplished by networks with just four neurons (three interneurons and one output). We show that evolving the networks in the presence of noise and variation of the intervals of silence between signals biases the solutions towards networks that can maintain their states (a form of memory), while the majority of networks evolved without variable intervals between signals cannot do so. We demonstrate that in most networks, the evolutionary process leads to the presence of superfluous connections that can be pruned without affecting the ability of the networks to perform the task and, if the unpruned network can maintain memory, so does the pruned network. We then analyse how these small networks can perform their tasks, using a paradigm of finite state transducers. This analysis shows that self-excitatory loops (autapses) in these networks are crucial for both the recognition of the pattern and for memory maintenance.

Keywords

Temporal pattern recognition Spiking neural networks Ex-loops Self-loops Artificial evolution Minimal cognition Complex networks Genetic algorithm Finite state transducer 

Notes

Acknowledgements

This work was supported by the Polish National Science Center (project EvoSN, UMO-2013/08/M/ST6/00922). MY acknowledges the support of the KNOW RNA Research Center in Poznan (No. 01/KNOW2/2014) and POWR.03.02.00-00-I006/17.

References

  1. 1.
    Ahissar, E., Arieli, A.: Figuring space by time. Neuron 32, 185–201 (2001)CrossRefGoogle Scholar
  2. 2.
    Anderson, J.S., Lampl, I., Gillespie, D.C., Ferster, D.: The contribution of noise to contrast invariance of orientation tuning in cat visual cortex. Science 290, 1968–1972 (2000)CrossRefGoogle Scholar
  3. 3.
    Bialek, W., Rieke, F., van Steveninck, R.R.d.R., Warland, D., et al.: Reading a neural code. In: Neural Information Processing Systems, pp. 36–43 (1989)Google Scholar
  4. 4.
    Burnstock, G.: Autonomic neurotransmission: 60 years since sir Henry Dale. Annu. Rev. Pharmacol. Toxicol. 49, 1–30 (2009)CrossRefGoogle Scholar
  5. 5.
    Decharms, R.C., Zador, A.: Neural representation and the cortical code. Annu. Rev. Neurosci. 23, 613–647 (2000)CrossRefGoogle Scholar
  6. 6.
    Destexhe, A., Rudolph, M., Fellous, J.M., Sejnowski, T.: Fluctuating synaptic conductances recreate in vivo-like activity in neocortical neurons. Neuroscience 107, 13–24 (2001)CrossRefGoogle Scholar
  7. 7.
    Destexhe, A., Paré, D.: Impact of network activity on the integrative properties of neocortical pyramidal neurons in vivo. J. Neurophysiol. 81, 1531–1547 (1999)CrossRefGoogle Scholar
  8. 8.
    Faisal, A.A., Selen, L.P., Wolpert, D.M.: Noise in the nervous system. Nat. Rev. Neurosci. 9, 292–303 (2008)CrossRefGoogle Scholar
  9. 9.
    Finn, I.M., Priebe, N.J., Ferster, D.: The emergence of contrast-invariant orientation tuning in simple cells of cat visual cortex. Neuron 54, 137–152 (2007)CrossRefGoogle Scholar
  10. 10.
    Florian, R.V.: Biologically inspired neural networks for the control of embodied agents. Center for Cognitive and Neural Studies (Cluj-Napoca, Romania), Tech. rep. Coneural-03-03 (2003)Google Scholar
  11. 11.
    Gerstner, W., Kempter, R., van Hemmen, J.L., Wagner, H.: A neuronal learning rule for sub-millisecond temporal coding. Nature 383, 76–78 (1996)CrossRefGoogle Scholar
  12. 12.
    Huxter, J., Burgess, N., Okeefe, J.: Independent rate and temporal coding in hippocampal pyramidal cells. Nature 425, 828–832 (2003)CrossRefGoogle Scholar
  13. 13.
    Jacobson, G., et al.: Subthreshold voltage noise of rat neocortical pyramidal neurones. J. Physiol. 564, 145–60 (2005)CrossRefGoogle Scholar
  14. 14.
    Joris, P., Yin, T.: A matter of time: internal delays in binaural processing. Trends Neurosci. 30, 70–78 (2007)CrossRefGoogle Scholar
  15. 15.
    Laurent, G.: Dynamical representation of odors by oscillating and evolving neural assemblies. Trends Neurosci. 19, 489–496 (1996)CrossRefGoogle Scholar
  16. 16.
    Maex, R., Steuber, V.: The first second: models of short-term memory traces in the brain. Neural Netw. 22, 1105–1112 (2009)CrossRefGoogle Scholar
  17. 17.
    Major, G., Tank, D.: Persistent neural activity: prevalence and mechanisms. Curr. Opin. Neurobiol. 14, 675–684 (2004)CrossRefGoogle Scholar
  18. 18.
    Marder, E.: Variability, compensation, and modulation in neurons and circuits. Proc. Nat. Acad. Sci. U.S.A. 108, 15542–15548 (2011)CrossRefGoogle Scholar
  19. 19.
    Natschläger, T., Maass, W.: Spiking neurons and the induction of finite state machines. Theoret. Comput. Sci. 287, 251–265 (2002)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Naud, R., Marcille, N., Clopath, C., Gerstner, W.: Firing patterns in the adaptive exponential integrate-and-fire model. Biol. Cybern. 99, 335–347 (2008)MathSciNetCrossRefGoogle Scholar
  21. 21.
    Paré, D., Shink, E., Gaudreau, H., Destexhe, A., Lang, E.J.: Impact of spontaneous synaptic activity on the resting properties of cat neocortical pyramidal neurons in vivo. J. Neurophysiol. 79, 1450–1460 (1998)CrossRefGoogle Scholar
  22. 22.
    Prinz, A.A., Bucher, D., Marder, E.: Similar network activity from disparate circuit parameters. Nat. Neurosci. 7, 1345–1352 (2004)CrossRefGoogle Scholar
  23. 23.
    Rieke, F., Warland, D., de Ruyter van Steveninck, R., Bialek, W.: Spikes: Exploring the Neural Code. MIT Press, Cambridge (1999)zbMATHGoogle Scholar
  24. 24.
    Rutishauser, U., Douglas, R.J.: State-dependent computation using coupled recurrent networks. Neural Comput. 21, 478–509 (2009)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Isaacson, J.S.: Odor representations in mammalian cortical circuits. Curr. Opin. Neurobiol. 20, 328–31 (2010)CrossRefGoogle Scholar
  26. 26.
    Saada, R., Miller, N., Hurwitz, I., Susswein, A.J.: Autaptic excitation elicits persistent activity and a plateau potential in a neuron of known behavioral function. Curr. Biol. 19, 479–84 (2009)CrossRefGoogle Scholar
  27. 27.
    Seung, H.S., Lee, D.D., Reis, B.Y., Tank, D.W.: The autapse: a simple illustration of short-term analog memory storage by tuned synaptic feedback. J. Comput. Neurosci. 9, 171–185 (2000)CrossRefGoogle Scholar
  28. 28.
    Sipser, M.: Introduction to the Theory of Computation. International Thomson Publishing, Stamford (1996)CrossRefGoogle Scholar
  29. 29.
    Stacey, W., Durand, D.: Stochastic resonance improves signal detection in hippocampal neurons. J. Neurophysiol. 83, 1394–1402 (2000)CrossRefGoogle Scholar
  30. 30.
    Steuber, V., De Schutter, E.: Rank order decoding of temporal parallel fibre input patterns in a complex Purkinje cell model. Neurocomputing 44–46, 183–188 (2002)CrossRefGoogle Scholar
  31. 31.
    Steuber, V., Willshaw, D.J.: Adaptive leaky integrator models of cerebellar Purkinje cells can learn the clustering of temporal patterns. Neurocomputing 26–27, 271–276 (1999)CrossRefGoogle Scholar
  32. 32.
    Steuber, V., Willshaw, D.: A biophysical model of synaptic delay learning and temporal pattern recognition in a cerebellar Purkinje cell. J. Comput. Neurosci. 17, 149–164 (2004)CrossRefGoogle Scholar
  33. 33.
    Steuber, V., Willshaw, D., Ooyen, A.V.: Generation of time delays: simplified models of intracellular signalling in cerebellar Purkinje cells. Netw. Comput. Neural Syst. 17, 173–191 (2006)CrossRefGoogle Scholar
  34. 34.
    Thorpe, S., Fize, D., Marlot, C.: Speed of processing in the human visual system. Nature 381, 520–522 (1996)CrossRefGoogle Scholar
  35. 35.
    Tino, P., Mills, A.J.S.: Learning beyond finite memory in recurrent networks of spiking neurons. Neural Comput. 18, 591–613 (2005)MathSciNetCrossRefGoogle Scholar
  36. 36.
    Wang, C., et al.: Formation of autapse connected to neuron and its biological function. Complexity 2017, 1–9 (2017)MathSciNetzbMATHGoogle Scholar
  37. 37.
    Wiesenfeld, K., Moss, F.: Stochastic resonance and the benefits of noise: from ice ages to crayfish and squids. Nature 373, 33–36 (1995)CrossRefGoogle Scholar
  38. 38.
    Yaqoob, M., Wróbel, B.: Robust very small spiking neural networks evolved with noise to recognize temporal patterns. In: ALIFE 2018: Proceedings of the 2018 Conference on Artificial Life - MIT Press, pp. 665–672 (2018)Google Scholar
  39. 39.
    Yaqoob, M., Wróbel, B.: Very small spiking neural networks evolved to recognize a pattern in a continuous input stream. In: 2017 IEEE Symposium Series on Computational Intelligence (SSCI) - IEEE, pp. 3496–3503 (2017)Google Scholar
  40. 40.
    Yaqoob, M., Wróbel, B.: Very small spiking neural networks evolved for temporal pattern recognition and robust to perturbed neuronal parameters. In: Artificial Neural Networks and Machine Learning - ICANN, pp. 322–331 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Evolving Systems LaboratoryAdam Mickiewicz University in PoznanPoznanPoland
  2. 2.University of HertfordshireHatfieldUK

Personalised recommendations