Abstract
Perceptrons are one of the fundamental paradigms in artificial neural networks and a key processing scheme in supervised classification tasks. However, the algorithm they provide is given in terms of unrealistically simple processing units and connections and therefore, its implementation in real neural networks is hard to be fulfilled. In this work, we present a neural circuit able to perform perceptron’s computation based on realistic models of neurons and synapses. The model uses Wang-Buzsáki neurons with coupling provided by axodendritic and axoaxonic synapses (heterosynapsis). The main characteristics of the feedforward perceptron operation are conserved, which allows to combine both approaches: whereas the classical artificial system can be used to learn a particular problem, its solution can be directly implemented in this neural circuit. As a result, we propose a biologically-inspired system able to work appropriately in a wide range of frequencies and system parameters, while keeping robust to noise and error.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
F. Rosenblatt, Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms (Spartan Books, Washington, 1962)
D.E. Rumelhart, G.E. Hinton, R.J. Williams, Nature 323, 533 (1986)
J.J. Hopfield, Proc. Natl. Acad. Sci. USA 79, 2554 (1982)
J. Hertz, A. Krogh, R.G. Palmer, Introduction to the Theory of Neural Computation (Addison-Wesley, New York, 1991)
A.L. Hodgkin, A.F. Huxley, J. Physiol. 117, 500 (1952)
X.-J. Wang, Physiol. Rev. 90, 1195 (2010)
M. Bartos, I. Vida, P. Jonas, Nat. Rev. Neurosci. 8, 45 (2007)
R. Krahe, F. Gabbiani, Nat. Rev. Neurosci. 5, 13 (2004)
B.P. Bean, Nat. Rev. Neurosci. 8, 451 (2007)
W. Maass, Neural Networks 10, 1659 (1997)
Y. Kuramoto, Chemical Oscillations, Waves, Turbulence (Springer, New York, 1984)
T. Aoyagi, Phys. Rev. Lett. 74, 4075 (1995)
T. Aonishi, K. Kurata, M. Okada, Phys. Rev. Lett. 82, 2800 (1999)
T. Nishikawa, Y.-C. Lai, F.C. Hoppensteadt, Phys. Rev. Lett. 92, 108101 (2004)
P. Kaluza, T. Cioaca, Neurocomputing 97, 115 (2012)
P. Kaluza, Neurocomputing 118, 127 (2013)
S.M. Bohte, J.N. Kok, H. La Poutré, Neurocomputing 48, 17 (2002)
P. D’Souza, S.-C. Liu, R.H.R. Hahnloser, Proc. Natl. Acad. Sci. USA 107, 4722 (2010)
L. Serrano, Mol. Syst. Biol. 3, 158 (2007)
X.-J. Wang, G. Buzsáki, J. Neurosci. 16, 6402 (1996)
J.A. White, C.C. Chow, J. Ritt, C. Soto-Treviño, N. Kopell, J. Comput. Neurosci. 5, 5 (1998)
D. Hansel, G. Mato, Neural Comput. 15, 1 (2003)
J.A. White, M.I. Banks, R.A. Pearce, N.J. Kopell, Proc. Natl. Acad. Sci. USA 97, 8128 (2000)
P.H.E. Tiesinga, J.-M. Fellous, J.V. José, T.J. Sejnowski, Hippocampus 11, 251 (2001)
P.H.E. Tiesinga, T.J. Sejnowski, Neural Comput. 16, 251 (2004)
P.H. Tiesinga, J.-M. Fellous, E. Salinas, J.V. José, T.J. Sejnowski, J. Physiol. 98, 296 (2004)
G. Mato, I. Samengo, Neural Comput. 20, 2418 (2008)
A.B. MacDermott, L.W. Role, S.A. Siegelbaum, Ann. Rev. Neurosci. 22, 443 (1999)
C.H. Bailey, M. Giustetto, Y.-Y. Huang, R.D. Hawkins, E.R. Kandel, Nat. Rev. Neurosci. 1, 11 (2000)
A.J. Cochilla, S. Alford, J. Neurosci. 19, 193 (1999)
D. Schmitz, S. Schuchmann, A. Fisahn, A. Draguhn, E.H. Buhl, E. Petrasch-Parwez, R. Dermietzel, U. Heinemann, R.D. Traub, Neuron 31, 831 (2001)
B. Lamotte D’Incamps, C. Meunier, M.-L. Monnet, L. Jami, D. Zytnicki, J. Comput. Neurosci. 5, 141 (1998)
P. Peretto, J.J. Niez, Biol. Cybern. 54, 53 (1986)
J.J. Arenzon, R.M.C. de Almeida, Phys. Rev. E 48, 4060 (1993)
R. Rojas, Neural Networks – A Systematic Introduction (Springer-Verlag, Berlin, 1996)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kaluza, P., Urdapilleta, E. Perceptron-like computation based on biologically-inspired neurons with heterosynaptic mechanisms. Eur. Phys. J. B 87, 236 (2014). https://doi.org/10.1140/epjb/e2014-50322-y
Received:
Revised:
Published:
DOI: https://doi.org/10.1140/epjb/e2014-50322-y