Abstract
Three conjectures are presented that form the methodological link between Volterra models (mappings) and a popular class of artificial neural networks (multi-layer perceptrons). The first conjecture elucidates the equivalence between these two types of nonlinear mapping and shows how we can achieve a network implementation of a Volterra model by employing proper linear input transformations and polynomial activation functions in the hidden units; while the output unit(s) may be simple adder(s). The second conjecture outlines the trade-offs between general polynomial and fixed sigmoidal activation functions traditionally used in multilayer perceptrons. The former are more flexible in defining nonlinear mappings; while thelatter, being far more restrictive, lead to increased numbers of hidden units and heavier computational burden during training via back-propagation. In general, an infinite number of sigmoidal hidden units is required to represent exactly a Volterra model (mapping) or a network with (finite) polynomial hidden units. The third conjecture extends the results for continous-output models to binary-(or spike-)output models/mappings, often encountered in neural networks. These conjectures collectively point to the potential versatility and efficiency of a class of networks that utilize polynomial activation functions in the hidden units and linear output unit(s) with fixed weights. Practical procedures for optimal use of these networks are currently developed.
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
Blum, E.K. and Li, L.K. (1991) Approximation theory and feedforward networks. Neural Networks, 4:511–515.
Cybenko, G. (1989) Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals & Systems, 2:303–314.
de Figueiredo, R.J.P. (1980) Implications and applications of Kolmogorov’s superposition theorem. IEEE Trans. Autom. Contr., 25:1227–1231.
Funahashi, K.-I. (1989) On the approximate realization of continuous mappings by neural networks. Neural Networks, 2:183–192.
Hornik, K., Stinchcombe, M. and White, H. (1989) Multi-layer feedforward networks are universal approximators. Neural Networks, 2:359–366.
Ito, (1991) Neural Networks, 4:385–394.
Kolmogorov, A.N. (1957) On the representation of continuous functions of several variables by superposition of continuous functions of one variable and addition. Doklady Akademii Nauk. SSSR, 114:953–956; AMS Transi. 2:55–59, (1963).
Marmarelis, V.Z. (1989) Signal transformation and coding in neural systems. IEEE Trans. Biomed. Eng., 36:15–24.
Marmarelis, VIZ. and Orme, M.E. (1993) Modeling of neuronal systems by use of neuronal modes. IEEE Trans. Biomed. Eng., 40:1149–1158.
Rosenblatt, F. (1962) Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms. Spartan Books, Washington, D.C.
Rumelhart, D.E. and McClelland, J.L. (1986) (Eds.) Parallel Distributed Processing, Vol. I. and II., MIT Press, Cambridge, Massachussetts.
Sprecher, D.A. (1972) An improvement in the superposition theorem of Kolmogorov. /. Math. Anal. Amol, 38:208–213.
Widrow, B. and Lehr, M.A. (1990) 30 years of adaptive neural networks: Perceptron, madaline and back propagation. Proc. IEEE, 78:1415–1442.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer Science+Business Media New York
About this chapter
Cite this chapter
Marmarelis, V.Z. (1994). Three Conjectures on Neural Network Implementations of Volterra Models (Mappings). In: Marmarelis, V.Z. (eds) Advanced Methods of Physiological System Modeling. Springer, Boston, MA. https://doi.org/10.1007/978-1-4757-9024-5_15
Download citation
DOI: https://doi.org/10.1007/978-1-4757-9024-5_15
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4757-9026-9
Online ISBN: 978-1-4757-9024-5
eBook Packages: Springer Book Archive