Abstract
This paper describes a method of constructing one-hidden layer feedforward linear threshold networks to represent Boolean functions (or partially-defined Boolean functions). The first step in the construction is sequential linear separation, a technique that has been used by a number of researchers [7, 11, 2]. Next, from a suitable sequence of linear separations, a threshold network is formed. The method described here results in a threshold network with one hidden layer. We compare this approach to the standard approach based on a Boolean function’s disjunctive normal form and to other approaches based on sequential linear separation [7, 11].
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Anthony, M.: Discrete Mathematics of Neural Networks: Selected Topics. Society for Industrial and Applied Mathematics, Philadeplhia (2001)
Anthony, M.: On data classification by iterative linear partitioning. Discrete Applied Mathematics 144(1-2), 2–16 (2004)
Cover, T.M.: Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition. IEEE Trans. on Electronic Computers EC-14, 326–334 (1965)
Hammer, P.L., Ibaraki, T., Peled., U.N.: Threshold numbers and threshold completions. Annals of Discrete Mathematics 11, 125–145 (1981)
Jeroslow, R.G.: On defining sets of vertices of the hypercube by linear inequalities. Discrete Mathematics 11, 119–124 (1975)
Krause, M.: On the computational power of boolean decision lists. In: Alt, H., Ferreira, A. (eds.) STACS 2002. LNCS, vol. 2285, pp. 372–383. Springer, Heidelberg (2002)
Marchand, M., Golea, M.: On Learning Simple Neural Concepts: from Halfspace Intersections to Neural Decision Lists. Network: Computation in Neural Systems 4, 67–85 (1993)
Marchand, M., Golea, M., Ruján, P.: A convergence theorem for sequential learning in two-layer perceptrons. Europhys. Lett. 11, 487 (1990)
Rivest, R.R.: Learning Decision Lists. Machine Learning 2(3), 229–246 (1987)
Siu, K.Y., Rowchowdhury, V., Kalaith, T.: Discrete Neural Computation: A Theoretical Foundation. Prentice Hall, Englewood Cliffs (1995)
Tajine, M., Elizondo, D.: Growing methods for constructing Recursive Deterministic Perceptron neural networks and knowledge extraction. Artificial Intelligence 102, 295–322 (1998)
Tajine, M., Elizondo, D.: The recursive deterministic perceptron neural network. Neural Networks 11, 1571–1588 (1998)
Turán, G., Vatan, F.: Linear decision lists and partitioning algorithms for the construction of neural networks. In: Foundations of Computational Mathematics: selected papers of a conference, Rio de Janeiro, pp. 414–423. Springer, Heidelberg (1997)
Zuev, A., Lipkin, L.I.: Estimating the efficiency of threshold representations of Boolean functions. Cybernetics 24, 713–723 (1988); Translated from Kibernetika (Kiev) 6, 29–37 (1988)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Anthony, M. (2009). On Constructing Threshold Networks for Pattern Classification. In: Franco, L., Elizondo, D.A., Jerez, J.M. (eds) Constructive Neural Networks. Studies in Computational Intelligence, vol 258. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04512-7_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-04512-7_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04511-0
Online ISBN: 978-3-642-04512-7
eBook Packages: EngineeringEngineering (R0)