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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The original experimental findings of Adrian E [1] were reported as the number of spikes within a time window after the stimulus onset and so it is probably more accurate to associate those measurements as count code.
References
E. Adrian, The Basis of Sensation: The Actions of the Sense Organs (Lowe and Brydone Printers Ltd., London, 1928)
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)
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
C. Carr, M. Konishi, Axonal delay lines for time measurement in the owl’s brainstem. Proc. Natl. Acad. Sci. 85(21), 8311–8315 (1988)
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)
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)
R. Florian, Tempotron-like learning with resume, in Artificial Neural Networks-ICANN 2008 (Springer, 2008), pp. 368–375
R. Florian, The chronotron: a neuron that learns to fire temporally precise spike patterns. PLoS ONE 7(8), e40,233 (2012)
E. Gardner, The space of interactions in neural network models. J. Phys. A: Math. Gen. 21(1), 257 (1988)
R. Gütig, H. Sompolinsky, The tempotron: a neuron that learns spike timing-based decisions. Nat. Neurosci. 9, 420–428 (2006). doi:10.1038/nn1643
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
E. Izhikevich, Polychronization: computation with spikes. Neural Comput. 18(2), 245–282 (2006)
R. Johansson, I. Birznieks, First spikes in ensembles of human tactile afferents code complex spatial fingertip events. Nature Neurosci. 7(2), 170–177 (2004)
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)
P. Knüsel, R. Wyss, P. König, P.F. Verschure, Decoding a temporal population code. Neural Comput. 16(10), 2079–2100 (2004)
R. Legenstein, C. Näger, W. Maass, What can a neuron learn with spike-timing-dependent plasticity? Neural Comput. 17(11), 2337–2382 (2005)
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
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
M. Minsky, S. Papert, Perceptrons: An Introduction to Computational Geometry (MIT Press, Cambridge, Mass, 1969)
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)
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)
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. 1357–1365
J. O’Keefe, N. Burgess, Geometric determinants of the place fields of hippocampal neurons. Nature 381(6581), 425–428 (1996)
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)
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)
F. Rieke, Spikes: Reading the Neural Code (The MIT Press, 1997)
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
M. van Rossum, A novel spike distance. Neural Comput. 13(4), 751–763 (2001)
S. Sheik, Autonomous learning in neuromorphic systems for recognition of spatio-temporal spike patterns. Ph.D. thesis, ETH-Zürich (2013)
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)
W. Singer, Time as coding space? Curr. Opin. Neurobiol. 9(2), 189–194 (1999)
K. Stiefel, J. Tapson, A. van Schaik, Temporal order detection and coding in nervous systems. Neural Comput. 25(2), 510–531 (2013)
S. Thorpe, A. Delorme, R.V. Rullen et al., Spike-based strategies for rapid processing. Neural Netw. 14(6–7), 715–725 (2001)
J. Victor, K. Purpura, Metric-space analysis of spike trains: theory, algorithms and application. Netw.: Comput. Neural Syst. 8(2), 127–164 (1997)
J. Vreeken, Spiking neural networks, an introduction. Technical Report UU-CS (2003-008), 1–5 (2003)
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
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)
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.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Sheik, S. (2017). Spike Based Information Processing in Spiking Neural Networks. In: In, V., Longhini, P., Palacios, A. (eds) Proceedings of the 4th International Conference on Applications in Nonlinear Dynamics (ICAND 2016). ICAND 2016. Lecture Notes in Networks and Systems, vol 6. Springer, Cham. https://doi.org/10.1007/978-3-319-52621-8_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-52621-8_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-52620-1
Online ISBN: 978-3-319-52621-8
eBook Packages: EngineeringEngineering (R0)