Abstract
We introduce a learning algorithm for feed-forward neural networks with synapses which only can take a discrete number of values. The main novelty respect to other discrete learning techniques is a different strategy in the search for solutions which turns out to be quite effective. Generalizations to any arbitrary distribution of discrete weights are straightforward.
Preview
Unable to display preview. Download preview PDF.
References
H. Gutfreund and Y. Stein, Capacity of neural networks with discrete synaptic couplings, J. Phys. A 23, 2613–2630, 1990.
W. Krauth and M. Mezard, Storage capacity of memory networks with binary couplings, J. Phys. France 50, 3057–3066, 1989.
H. Kohler, Adaptive genetic algorithm for the binary perceptron problem, J. Phys. A 23, L1265–1271, 1990.
E. Amaldi and S. Nicolis, Stability-capacity diagram of a neural network with Ising bonds, J. Phys. France 50, pp. 2333–2345, 1989.
S.I. Gallant, Perceptron-based learning algorithms, IEEE Trans. on neural networks, vol. 1, no. 2, pp. 179–191, 1990.
H. Kohler, S. Diederich, W. Kinzel and M. Opper, Learning algorithm for a neural network with binary synapses, Z. Phys. B 78, 333–342, 1990.
C.J. Pérez Vicente, Learning algorithm for binary synapses, Proc. XI Sitges Conference (Sitges, Spain), pp. 167–174, 1990.
E. Gardner, The phase space of interactions in neural networks models, J. Phys. A 21, 257–270, 1988.
C.J. Pérez Vicente, J. Carrabina and E. Valderrama, Study of a learning algorithm for discrete synapses, Submitted to Network: Computation in neural systems.
H. Rao, Optimization theory and applications, Wiley Eastern Limited 1987.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vicente, C.J.P., Carrabina, J., Garrido, F., Valderrama, E. (1991). Learning algorithm for feed-forward neural networks with discrete synapses. In: Prieto, A. (eds) Artificial Neural Networks. IWANN 1991. Lecture Notes in Computer Science, vol 540. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0035889
Download citation
DOI: https://doi.org/10.1007/BFb0035889
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54537-8
Online ISBN: 978-3-540-38460-1
eBook Packages: Springer Book Archive