Abstract
We present various possiblllties to Implement adaptive behaviour of cable neurons and show their qualitative effect. We argue that Incorporating these possibllities In local learning rules (or schemes) can account for adaptation that combines spatial and temporal properties. Experiments with a phasic XOR explain why a local learning rule based on detection of coincidence of a high local potential In the cable and the arrival of an Input pulse, renders a network capable of performing the XOR function.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
A. J. Klaassen. Computing with cables: towards massively parallel neuro computers. PhD thesis. Delft University of Technology. Delft, the Netherlands, 1992.
L. H. Finkel and G. M. Edelman. “Population rules for synapses in networks.” In Synaptic Amotion (G. M. Edelman, W. E. Gall, and W. M. Cowan, eds.). pp. 711–757. New York: Wiley. 1987.
A. J. Klaassen and A. Dev. “Learning pulse coded spatio-temporal neurons with a local learning rule.” in IJCNN. vol. 1. (Seattle. WA). pp. 829–837. 1991.
D. L. Alkon. “Calcium-mediated reduction of ionic currents: A biophysical memory trace.” Science, vol. 226. pp. 1037–1045. Nov. 1984.
D. L. Alkon. “Memory storage and neural systems.” Scientific American, pp. 27–34. Jul 1989.
Y. Qiao. “Learning in large optical networks.” in SPIE Aerospace Sensing. Science of Artificial Neural Networks. (Orlando. FL). 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag London Limited
About this paper
Cite this paper
Klaassen, A.J., Hoekstra, J. (1993). On the Adapative Capabilities of Pulse-Coded Cable Neurons. In: Gielen, S., Kappen, B. (eds) ICANN ’93. ICANN 1993. Springer, London. https://doi.org/10.1007/978-1-4471-2063-6_47
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2063-6_47
Published:
Publisher Name: Springer, London
Print ISBN: 978-3-540-19839-0
Online ISBN: 978-1-4471-2063-6
eBook Packages: Springer Book Archive