Abstract
Since their introduction, neural networks have become an accepted object of research in various disciplines. Most of these neural networks are implemented using digital hardware consisting of computers or dedicated processors.
Analogue implementations of artificial neurons, the elementary processing units, could be smaller than their digital counterparts, thus enabling more complex networks on a single chip. Conventional methods of learning cannot be used directly in these networks, due to practical limitations regarding on-chip interconnections. In order to achieve such a complexity, it is necessary to refine the neural networks.
This article proposes an artificial dendrite, one of the most important parts of the neuron. The artificial dendrite uses principles found in biology like active propagation and shaping of action potentials using active channels. A brief introduction in neurophysiology is given in order to explain the underlying mechanisms. The model is simulated in SPICE using models of conventional analogue electronic devices.
Preview
Unable to display preview. Download preview PDF.
References
Simon Haykin, Neural Networks, A Comprehensive Foundation, Prentice Hall, New Jersey, 1994.
Carver Mead, Analog VLSI and neural systems, Addison Wesley, 1989.
C.A. Mead and M.A. Mahowald, “A silicon model of early visual processing,” Neural Networks, no. 1, pp. 91–97, 1988.
R.H.S. Carpenter, Neurophysiology—Third edition, Arnold, London, 1996.
C. Koch, “Computation and the single neuron”, Nature, vol. 385, pp. 207–210, 1997.
Editorial, “Making sense of channel diversity,” Neuroscience vol 1, no. 1, pp. 169–170, 1998.
J. Hoekstra, “Single and multiple compartment models in neural networks,” in Computing Anticipatory Systems—CASYS'97 conference proceedings, Daniel M. Dubois, Ed., Liège, Belgium, 1997, CHAOS, pp. 626–641, AIP.
T. Bogart, Electronic devices and circuits—Third edition, Merril Prentice Hall, Columbus, Ohio, 1993.
P. Horowitz and W. Hill, The art of electronics—Second edition, Cambridge university press, 1996.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rouw, E., Hoekstra, J., van Roermund, A.H.M. (1999). An artificial dendrite using active channels. In: Mira, J., Sánchez-Andrés, J.V. (eds) Engineering Applications of Bio-Inspired Artificial Neural Networks. IWANN 1999. Lecture Notes in Computer Science, vol 1607. Springer, Berlin, Heidelberg . https://doi.org/10.1007/BFb0100484
Download citation
DOI: https://doi.org/10.1007/BFb0100484
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66068-2
Online ISBN: 978-3-540-48772-2
eBook Packages: Springer Book Archive