Abstract
Quantization of the synaptic weights is a central problem of hardware implementation of neural networks using numerival technology. In this paper, a particular linear threshold boolean function, called majority function is considered, whose synaptic weights are restricted to only three values: −1, 0, +1. Some results about the complexity of the circuits composed of such gates are reported. They show that this simple family of functions remains powerful in therm of circuit complexity. The learning problem with this subclass of threshold function is also studied and numerical experiments of different algorithms are reported.
Supported by grant 20-5637.88 of the Swiss National Science Foundation.
Preview
Unable to display preview. Download preview PDF.
References
M. Ajtai, Σ 11 formulae on finite structures, Anals of Pure and Applied Logic 24 (1984) pp. 1–48.
E. Amaldi and S. Nicolis, Stability-Capacity Diagram of a Neural Network with Ising Bonds, J. Physique 50 (1989) pp. 2333–2345.
E. Amaldi, E. Mayoraz and D. de Werra, Discrete Optimization Problems in Neural Network Design, Submitted to Discrete Applied Math.
E. Amaldi, On the Complexity of Training Perceptrons, Int. Conf. on Artificial Neural Networks, Helsinki Published by Elsvier (1991).
M. Furst, J.B. Saxe, M. Sipser, Circuits and the Polynomial-Time Hierarchy, Proceedings of 22 nd Annual IEEE Symp. on Fundations of Computer Science (1981) pp. 260–270.
F. Glover, Tabu Search, Part I, ORSA J. Computing 1(3) (1989) 190–206.
J. Hastad, Almost Optimal Lower Bounds for Small Depth Circuits, Proceedings of 18 th ACM Symp. on Theory of Computing (1986) pp. 6–20.
J. Hong, On connectionist models, Tech. Rep. 87-012, Dept of Computer Science University of Chicago, USA (1987).
W. Krauth and M. Mézard, Learning Algorithms with Optimal Stability in Neural Networks, J. Phys. A: Math Gen. 20 (1987) pp. L745–L752.
W. Krauth and M. Opper, Critical Storage Capacity of the J=±1 Neural Networks, J. Phys. A 22 (1989) pp. L519–L523.
R.J. McEliece, E.C. Posner, E.R. Rodemick and S.S. Venkatesh, The Capacity of the Hopfield Association Memory IEE Trans. on Information Theory IT-33 No. 4 (July 1987).
E. Mayoraz, Benchmark of Some Learning Algorithms for Single Layer and Hopfield Networks, Complex Systems 4 (1990) pp. 477–490.
W. Krauth and M. Mézard, Storage Capacity of Memory Networks with Binary Couplings, J. Phys. France 50 (1989) pp. 3057–3066.
J. Myhill and W. H. Kautz, On the size of Weights Required for Linear-Input Switching Functions, IRE Trans. on Electronic Computers EC 10 (1961).
L. Pitt and L.G. Valiant, Computational Limitations on Learning from Examples, Journal of the ACM 35 No. 4 (October 1988) pp. 965–984.
A.A. Razborov, Lower Bounds for the size of circuits of bounded depth with basis {∧, ⊗}, Math. Notes 41 (1987) pp. 333–338.
R. Smolensky, Algebraic Methods in the Theory of Lower Bounds for Boolean Circuit Complexity, Proceedings of 19 th ACM Symp. on Theory of Computing (1987) pp. 77–82.
K.Y. Siu and J. Bruck, On The Power of Threshold Circuits with Small Weights To appear in SIAM J. on Discr. Math.
S.S. Venkatesh, Directed Drift: A new Linear Threshold Algorithm for Learning Binary Weights On-Line, Presented to the Workshop on Neural Networks for Computing, Snowbird, Utah (April 1989).
M. Verleysen, B. Sirletti, A.M. Vandermeulebroecke and P.G.A. Jespers, Neural Networks for High-Storage Content-Addressable Memory: VLSI Circuit and Learning Algorithm, IEEE Journal of solid-state circuits vol. 24 No 3 (June 1989).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mayoraz, E. (1991). On the power of networks of majority functions. In: Prieto, A. (eds) Artificial Neural Networks. IWANN 1991. Lecture Notes in Computer Science, vol 540. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0035880
Download citation
DOI: https://doi.org/10.1007/BFb0035880
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