Abstract
Spiking neural networks constitute a modern neural network paradigm that overlaps machine learning and computational neurosciences. Spiking neural networks use neuron models that possess a great degree of biological realism. The most realistic model of the neuron is the one created by Alan Lloyd Hodgkin and Andrew Huxley. However, the Hodgkin–Huxley model, while accurate, is computationally very inefficient. Eugene Izhikevich created a simplified neuron model based on the Hodgkin–Huxley equations. This model has better computational efficiency than the original proposed by Hodgkin and Huxley, and yet it can successfully reproduce all known firing patterns. However, there are not many articles dealing with implementations of this model for a functional neural network. This study presents a spiking neural network architecture that utilizes improved Izhikevich neurons with the purpose of evaluating its speed and efficiency. Since the field of spiking neural networks has reinvigorated the interest in biological plausibility, biological realism was an additional goal. The network is tested on the correct classification of logic gates (including XOR) and on the iris dataset. Results and possible improvements are also discussed.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Notes
In the default implementation found in (Izhikevich, n.d.) the timestep is 0.5 ms.
References
Bellatreche A, McGuire LP, McGiniity M, Wu Xiang Q (2006) Evolutionary design of spiking neural networks. New Math Nat Comput 2(3):237–253
Bohte S, Kok J, Poutre HL (2002) Error backpropagationin temporally encoded networks ofspiking neurons. Neurocomputing 48:17–37
Bohte SM, Poutre HL, Kok JN (2001) Unsupervised clustering with spiking neurons by sparse temporal coding and multi-layer RBF networks. IEEE Trans Neural Netw, XX
Carnell A, Richardson D (2005) Linear algebrafor time series of spikes. In Proceedings European Symposium on Artificial Neural Networks
Eurich CW, Wilke SD (2000) Multidimensional encoding strategy of spiking neurons. Neural Comput 12(7):1519–1529
Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann Eugen 7(2):179–188
Gerstner W, Kistler WM (2002) Spiking neuron models. Cambridge University Press, Cambridge
Glackin C, Maguire L, McDaid L, Sayers H (2011) Receptive field optimisation and supervision of a fuzzy spiking neural network. Neural Netw 24:247–256
Hodgkin AL, Huxley A (1952) A quantitative description of membrane current and its application to conduction and excitation in nerve. J Physiol 117(4):500–544
Izhikevich EM (2003) Simple model of spiking neurons. IEEE Trans Neural Netw 14(6):1569–1572
Izhikevich EM (2004) Which model to use for cortical spiking neurons? IEEE Trans Neural Netw 15(5):1063–1070
Izhikevich E, n.d. Simple model of spiking neurons. http://www.izhikevich.org/publications/spikes.htm. Accessed 8 May 2011
Kasinski A, Ponulak F (2006) Comparison of supervised learning methods for spike time coding in spiking neural networks. Int J Appl Math Comput Sci 16(1):101–113
Lanella N, Back AD (2001) A spiking neural network architecture for nonlinear function approximation. Neural Netw 14(2001):933–939
Legenstein R, Naeger C, Maass W (2005) What can a neuron learn with spike-timing-dependent plasticity? Neural Comput 17(11):2337–2382
Maass W (1997) Networks of spiking neurons: the third generation of spiking neural networks. Neural Netw 10(9):1659–1671
Maass W, Bishop CM (2001) Pulsed neural networks. MIT Press, Cambridge
Miltra P, Miller R (2007) Normal and rebound impulse firing in retinal ganglion cells. Vis Neurosci 24(1):79–90
Minsky M, Papert S (1972) Perceptrons: an introduction to computational geometry, 2nd edn. The MIT Press, Cambridge
Nieder A, Dehaene S (2009) Representation of number in the brain. Ann Rev Neurosci 32:185–208
Person AL, Perkel DJ (2005) Unitary IPSPs drive precise Thalamic spiking in a circuit required for learning. Neuron 46(1):129–140
Pfister JP, Barber D, Gerstner W (2003) Optimal Hebbian learning: a probabilistic point of view. In: ICANN/ICONIP, 2003. Springer, Berlin
Ponulak F (2005). http://d1.cie.put.poznan.pl/~fp/. Accessed 25 Aug 2010
Rieke F, Warland D, Bialek W, de Ruyter van Steveninck R (1996) Spikes, exploring the neural code. The MIT Press, Cambridge
Shadlen MN, Newsome WT (1994) Noise, neural codes and cortical organization. Curr Opin Neurobiol 4(4):569–579
Sougne JP (2000) A learning algorithm for synfire chains. In: Connectionist models of learning, development and evolution, Liege, Belgium, 2000. Springer, Berlin
Super H, Romeo A (2011) Rebound spiking as a neural mechanism for surface filling-in. J Cogn Neurosci 23(2):491–501
Thorpe SJ, Delorme A, VanLurren R (2001) Spike-based strategies for rapid processing. Neural Netw 14(6–7):715–726
Valko M, Marques NC, Castellani M (2005) Evolutionary feature selection for spiking neural network pattern classifiers. In: Artificial intelligence, 2005. epia 2005. portuguese conference on. Covilha, 2005. IEEE Press, New York
Wang H (2009) Improvement of Izhikevich’s neuronal and neural network model. In: International conference on information engineering and computer science, Wuhan, China, 2009. IEEE Press, New York
Wu Q et al (2007) Edge detection based on spiking neural network model. In: Lectures notes in computer science, 4682/2007, pp 26–34
Xiaoli T, Howard ME (2004) Data clustering via spiking neural networks through spike timing-dependent plasticity. In: International conference on artificial intelligence, 2004
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kampakis, S. Improved Izhikevich neurons for spiking neural networks. Soft Comput 16, 943–953 (2012). https://doi.org/10.1007/s00500-011-0793-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-011-0793-1