https://doi.org/10.1140/epjb/e2014-50322-y
Regular Article
Perceptron-like computation based on biologically-inspired neurons with heterosynaptic mechanisms
1 Instituto de Ciencias Básicas,
Universidad Nacional de Cuyo. Padre Contreras 1300, 5500
Mendoza,
Argentina
2 Consejo Nacional de Investigaciones
Científicas y Técnicas, Buenos
Aires, Argentina
3 División de Física Estadística e
Interdisciplinaria, Centro Atómico Bariloche, Av. E. Bustillo Km 9.500, S.C. de Bariloche,
8400
Río Negro,
Argentina
a
e-mail: pkaluza@mendoza-conicet.gob.ar
Received:
19
May
2014
Received in final form:
22
August
2014
Published online:
20
October
2014
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.
Key words: Statistical and Nonlinear Physics
© EDP Sciences, Società Italiana di Fisica, Springer-Verlag, 2014