ArticlesNo Access

SPAN: SPIKE PATTERN ASSOCIATION NEURON FOR LEARNING SPATIO-TEMPORAL SPIKE PATTERNS

AMMAR MOHEMMED

Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, New Zealand

Search for more papers by this author

STEFAN SCHLIEBS

Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, New Zealand

Search for more papers by this author

SATOSHI MATSUDA

Department of Mathematical Information Engineering, Nihon University, Japan

Search for more papers by this author

, and

NIKOLA KASABOV

Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, New Zealand

Institute for Neuroinformatics, ETH and University of Zurich, Switzerland

Search for more papers by this author

https://doi.org/10.1142/S0129065712500128Cited by:218 (Source: Crossref)

Abstract

Spiking Neural Networks (SNN) were shown to be suitable tools for the processing of spatio-temporal information. However, due to their inherent complexity, the formulation of efficient supervised learning algorithms for SNN is difficult and remains an important problem in the research area. This article presents SPAN — a spiking neuron that is able to learn associations of arbitrary spike trains in a supervised fashion allowing the processing of spatio-temporal information encoded in the precise timing of spikes. The idea of the proposed algorithm is to transform spike trains during the learning phase into analog signals so that common mathematical operations can be performed on them. Using this conversion, it is possible to apply the well-known Widrow–Hoff rule directly to the transformed spike trains in order to adjust the synaptic weights and to achieve a desired input/output spike behavior of the neuron. In the presented experimental analysis, the proposed learning algorithm is evaluated regarding its learning capabilities, its memory capacity, its robustness to noisy stimuli and its classification performance. Differences and similarities of SPAN regarding two related algorithms, ReSuMe and Chronotron, are discussed.

Keywords:

References

W. Gerstner and W. M. Kistler , Spiking Neuron Models: Single Neurons, Populations, Plasticity ( Cambridge University Press , Cambridge, MA , 2002 ) . Crossref, Google Scholar
W. Maass, Neural Networks 10(9), 1659 (1997). Crossref, Web of Science, Google Scholar
W. Maass and C. M. Bishop (eds.) , Pulsed Neural Networks ( MIT Press , Cambridge, MA, USA , 1999 ) . Google Scholar
W. Maass, Pulsed Neural Networks (MIT Press, Cambridge, MA, USA, 1999) pp. 55–85. Google Scholar
S. Ghosh-Dastidar and H. Adeli, Int. J. Neural Syst. 19(4), 295 (2009). Link, Web of Science, Google Scholar
W. Maass and A. M. Zador, Neural Comput. 11(4), 903 (1999). Crossref, Medline, Web of Science, Google Scholar
M. Tsodyks, K. Pawelzik and H. Markram, Neural Comput. 10(4), 821 (1998). Crossref, Medline, Web of Science, Google Scholar
S. M. Bohte, Nat. Comput. 3, 195 (2004). Crossref, Google Scholar
R. VanRullen, R. Guyonneau and S. J. Thorpe, Trends Neurosci. 28(1), 1 (2005). Crossref, Medline, Web of Science, Google Scholar
P. Tiesinga, J. Fellous and T. J. Sejnowski, Nat. Rev. Neurosci. 9(2), 97 (2008). Crossref, Medline, Web of Science, Google Scholar
D. A. Buttset al., Nature 449(7158), 92 (2007). Crossref, Medline, Web of Science, Google Scholar
B. Szatmry and E. M. Izhikevich, PLoS Comput. Biol. 6(8), 1 (2010). Web of Science, Google Scholar
J. Hopfield, Nature 376, 33 (1995). Crossref, Medline, Web of Science, Google Scholar
S. M. Bohte, J. N. Kok and J. A. L. Poutré, Neurocomputing 48(4), 17 (2002). Crossref, Web of Science, Google Scholar
A. K. Vidybida, Int. J. Neural Syst. 21(3), 187 (2011). Link, Web of Science, Google Scholar
N. Kasabov , R. Schliebs and H. Kojima , IEEE Trans. Auton. Mental Develop . Google Scholar
A. Jahangiri and D. M. Durand, Int. J. Neural Syst. 21(2), 127 (2011). Link, Web of Science, Google Scholar
N. R. Luqueet al., Int. J. Neural Syst. 21(5), 385 (2011). Link, Web of Science, Google Scholar
U. R. Acharyaet al., Int. J. Neural Syst. 20(6), 509 (2010). Link, Web of Science, Google Scholar
J. Iglesias and A. E. P. Villa, Int. J. Neural Syst. 18(4), 267 (2008). Link, Web of Science, Google Scholar
M. O. Halloranet al., Prog. Electromagn. Res. C 113, 413 (2011). Crossref, Web of Science, Google Scholar
T. J. Strainet al., Int. J. Neural Syst. 20(6), 463 (2010). Link, Web of Science, Google Scholar
S. G. Wysoski, L. Benuskova and N. Kasabov, Neural Networks 23, 819 (2010). Crossref, Medline, Web of Science, Google Scholar
S. Ghosh-Dastidar and H. Adeli, Neural Networks 22(10), 1419 (2009). Crossref, Medline, Web of Science, Google Scholar
J. Peandrez-Carrascoet al., Spike-based convolutional network for real-time processing, Proc. 2010 20th Int. Conf. Pattern Recognition, ICPR '10 (IEEE Computer Society, Washington, DC, USA, 2010) pp. 3085–3088. Google Scholar
S. Soltic and N. K. Kasabov, Int. J. Neural Syst. 20(6), 437 (2010). Link, Web of Science, Google Scholar
S. P. Johnstonet al., Int. J. Neural Syst. 20(6), 447 (2010). Link, Web of Science, Google Scholar
E. Nichols, L. J. McDaid and N. H. Siddique, Int. J. Neural Syst. 20(6), 501 (2010). Link, Web of Science, Google Scholar
I. Uysal, H. Sathyendra and J. Harris, Int. J. Appl. Math. Comput. Sci. 18, 129 (2008). Crossref, Web of Science, Google Scholar
S. Deneve, Neural Comput. 20(1), 91 (2008). Crossref, Medline, Web of Science, Google Scholar
S. Ghosh-Dastidar and H. Adeli, Integrated. Comput.-Aided Eng. 14, 187 (2007). Crossref, Web of Science, Google Scholar
L. Bako, Brief. Bioinform. 11(3), 348 (2010). Crossref, Medline, Web of Science, Google Scholar
W. Maass, T. Natschläger and H. Markram, Neural Comput. 14(11), 2531 (2002). Crossref, Medline, Web of Science, Google Scholar
S. J. Thorpeet al., Neurocomputing 60, 857 (2004). Google Scholar
S. M. Bohte, J. N. Kok and J. A. L. Poutré, ESANN 419 (2000). Google Scholar
D. E. Rumelhart, G. E. Hinton and R. J. Williams, Nature 323, 533 (1986). Crossref, Web of Science, Google Scholar
J. Xin and M. Embrechts, Supervised learning with spiking neural networks, Int. Joint Conf. Neural Networks, IJCNN '013 (IEEE Press, 2001) pp. 1772–1777. Google Scholar
B. Schrauwen and J. van Campenhout , Improving SpikeProp: Enhancements to an error-backpropagation rule for spiking neural networks , Proc. 15th ProRISC Workshop ( 2004 ) . Google Scholar
R. Gutig and H. Sompolinsky, Nat. Neurosci. 9(3), 420 (2006). Crossref, Medline, Web of Science, Google Scholar
F. Ponulak and A. Kasiński, Neural Comput. 22(2), 467 (2010). Crossref, Medline, Web of Science, Google Scholar
R. V. Florian, The chronotron: A neuron that learns to fire temporally-precise spike patterns (2010) http://precedings.nature.com/documents/5190/version/1 . Google Scholar
F. Ponulak, ReSuMe — new supervised learning method for spiking neural networks, Technical report, Institute of Control and Information Engineering, Poznań University of Technology, Poznań, Poland (2005) . Google Scholar
R. Legenstein, C. Naeger and W. Maass, Neural Comput. 17(11), 2337 (2005). Crossref, Medline, Web of Science, Google Scholar
C. Bellet al., Nature 387, 278 (1997). Crossref, Medline, Web of Science, Google Scholar
B. Widrow and M. Lehr, Proc. IEEE 78(9), 1415 (1990). Crossref, Web of Science, Google Scholar
F. Ponulak and A. Kasinski, ReSuMe learning method for spiking neural networks dedicated to neuroprostheses control, Proc. EPFL LATSIS Symposium 2006, Dynamical Principles for Neuroscience and Intelligent Biomimetic Devices (2006) pp. 119–120. Google Scholar
R. V. Florian, Neural Comput. 19(6), 1468 (2007). Crossref, Medline, Web of Science, Google Scholar
J. D. Victor and K. P. Purpura, Network: Comput. Neural Syst. 8(2), 127 (1997). Crossref, Web of Science, Google Scholar
M. C. van Rossum, Neural Comput. 13(4), 751 (2001). Crossref, Medline, Web of Science, Google Scholar
A. Mohemmedet al., Optimization of spiking neural networks with dynamic synapses for spike sequence generation using PSO, Int. Joint Conf. Neural Networks, IJCNN 2011 (IEEE Press, San Jose, California, USA, 2011) pp. 2969–2974. Google Scholar
A. Mohemmed, S. Schliebs, S. Matsuda and N. Kasabov, Method for training a spiking neuron to associate input-output spike trains, to appear in Engineering Applications of Neural Networks, EANN 2011 (Springer Verlag, Corfu, Greece, 2011) . Google Scholar
E. Nordlie, M.-O. Gewaltig and H. E. Plesser, PLoS Comput. Biol. 5(8), (2009). Medline, Web of Science, Google Scholar
M.-O. Gewaltig and M. Diesmann, Scholarpedia 2(4), 1430 (2007). Crossref, Google Scholar
B. Schrauwen and J. V. Campenhout, Neurocomputing 70, 1247 (2007). Crossref, Web of Science, Google Scholar
F. Ponulak, Appl. Math. Comput. Sci. 18(2), 117 (2008). Web of Science, Google Scholar
A. Mohemmed and N. Kasabov, Incremental learning algorithm for spike pattern classification, WCCI 2012 IEEE World Congress on Computational Intelligence (Brisbane, Australia, 2012) pp. 1227–1232. Google Scholar
N. Kasabov, Neural Netw. 23(1), 16 (2010). Crossref, Medline, Web of Science, Google Scholar
N. Kasabov, Evolving spiking neural networks and neurogenetic systems for spatio- and spectro-temporal data modelling and pattern recognition, IEEE WCCI 20127311, LNCS, eds. J. Liuet al. (Springer-Verlag, Berlin, Heidelberg, 2012) pp. 234–260. Google Scholar
K. Dhobleet al., On-line spatiotemporal pattern recognition with evolving spiking neural networks utilising address event representation, rank oder- and temporal spike learning, WCCI 2012 IEEE World Congress on Computational Intelligence (Brisbane, Australia, 2012) pp. 554–560. Google Scholar
X. Wanget al., Neurocomputing 71(6), 655 (2008). Crossref, Web of Science, Google Scholar
S. Moradi and G. Indiveri , A VLSI network of spiking neurons with an asynchronous static random access memory , Biomedical Circuits and Systems Conference BIOCAS ( IEEE Press , 2011 ) . Google Scholar
G. Indiviery and T. Horiuchi, Frontiers in Neuroscience 5, 118 (2011). Medline, Web of Science, Google Scholar