Abstract
This paper briefly describes the design principles for an implementation of an artificial neuron in the form of a in silicon integrated circuit based on junction charge-coupled device technology. The significant features of the design are: (1) the possibility to have fixed as well as variable weights, with analog values; (2) analog output values; (3) suitable to support pulse-coded neural network algorithms; and (4) realized in a standard bipolar technology. As a simple example a McCulloch-Pitts neuron is fabricated and tested at a clock frequency of 40 MHz.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Psaltis, D., Sage, J., ‘Advanced implementation Technology, Part IV of the DARPA Neural Network Study’, Fairfax: AFCEA International Press, 1988.
Sage, J.P., Thompson, K., Withers, R.S., ‘An Artificial Neural Network Intergrated Circuit Based on MNOS/CCD Principles’, AIP Conf. Proc. 151, 381, 1986.
Hoekstra, J., ‘Simple JCCD Logic at 20 MHz’, Electronics Letters, Vol. 23, 246, 1987.
May, E.P., van der Klauw, C.L.M., Kleefstra, M., and Wolsheimer, E.A., ‘Junction Charge-Coupled Logic (JCCL)’, IEEE Journal of Solid-State Circuits, 1983, Vol. SC-18, pp 767–772.
Hoekstra, J., Some Models and Implementations of Digital Logic Functions Using Junction Charge-Coupled Devices, PhD-thesis, Delft University of Technology, 1988.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Hoekstra, J. (1990). An Integrated Artificial Neuron Based on Junction-CCD Technology. In: International Neural Network Conference. Springer, Dordrecht. https://doi.org/10.1007/978-94-009-0643-3_3
Download citation
DOI: https://doi.org/10.1007/978-94-009-0643-3_3
Publisher Name: Springer, Dordrecht
Print ISBN: 978-0-7923-0831-7
Online ISBN: 978-94-009-0643-3
eBook Packages: Springer Book Archive