Abstract
Most Artificial Neural Networks that are widely used today focus on approximating deterministic input-output mapping of nonlinear phenomena, and therefore, they can be well trained to represent the average behaviour of a nonlinear system. However, most natural phenomena are not only nonlinear but also highly variable. Deterministic neural networks do not adequately represent the variability observed in the natural settings of a system and therefore cannot capture the complexity of the whole system behaviour that is characterised by noise. This chapter implements a class of neural networks named Stochastic Neural Networks (SNNs) to simulate internal stochastic properties of natural and biological systems. Developing a suitable mathematical model for SNNs is based on the canonical representation of stochastic processes by means of Karhunen-Loève Theorem. In the implementation of this mathematical formulation for modelling nonlinear random processes from observed data, SNN is represented as a network of embedded deterministic neural networks, each representing a significant eigenfunction characterised by data, juxtaposed with random noise represented by White noise characterised by the corresponding eigenvalues. Two successful examples, including one from biology, are presented in the chapter to confirm the validity of the proposed SNN. Furthermore, analysis of internal working of SNNs provides an in-depth view of how SNNs work giving meaningful insights.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
F.R. Araujo, A.S. Henriques, A Stochastic neural model for fast identification of spatiotemporal sequences. Neural Process. Lett. 16, 277–292 (2002)
J. Bear, Hydrodynamic dispersion, in Flow Through Porous Media (Academic Press, New York, 1969)
M. Conti, C. Turchetti, Approximation of dynamical systems by continuous-time recurrent approximate identity neural network. Neural Parallel Sci. Comput. 2, 299–322 (1994)
G. Cybenko, Approximation by superposition of sigmoidal function. Math. Control Syst. Signals 2, 303–314 (1989)
K. Funahashi, On the approximate realization of continuous mappings by neural networks. Neural Netw. 2, 183–192 (1989)
I.I. Gilman, A.V. Skorohod, The Theory of Stochastic Processes (Springer, Berlin, 1974)
K. Hornik, M. Stinchcombe, H. White, Multilayer feedforward networks are universal approximators. Neural Netw. 2, 395–403(1989)
D. Kulasiri, W. Verwoerd, Stochastic Dynamics Modeling of Solute Transport in Porous Media. North Holland Applied Mathematics and Mechanics Series, vol. 44. (Elsevier Science, Amsterdam, 2002)
C.-C.J. Lin, J. Ghaboussi, Generating multiple spectrum compatible accelerograms using stochastic neural networks. Earthq. Eng. Struct. Dyn. 30, 1021–1042 (2001)
L. Ling, S. Samarasinghe, D. Kulasiri, Modelling variability in full-field displacement profiles and Poisson ratio of wood in compression using stochastic neural networks. Silva Fennica 43(5), 871–887 (2009)
J. Park, W. SandbergI, Universal approximation using radial-basis-function network. Neural Comput. 3, 246–257 (1991)
P.E. Pfeiffer, Probability for Application (Springer, New York, 1990)
D. Rosaci, Stochastic neural networks for transportation systems modeling. Appl. Artif. Intell. 12, 491–500 (1997)
S. Samarasinghe, Neural Networks for Applied Sciences and Engineering: From Fundamentals to Complex Pattern Recognition (Auerbach, Boca Raton, 2006)
S. Samarasinghe, G.D. Kulasiri, Displacement fields of wood in tension based on image processing: Part 1. Tension parallel- and perpendicular-to-grain and comparison with isotropic behaviour. Silva Fennica 34(3), 51–259 (2000)
S. Samarasinghe, G.D. Kulasiri, Displacement fields of wood in tension based on image processing: Part 2. Crack-tip displacement in mode-I and mixed-mode fracture. Silva Fennica 34(3), 261–274 (2000)
C. Turchetti, Stochastic Models of Neural Networks (IOS Press, Amsterdam, 2004)
R.J.M. Wiest, Fundamental Principles in groundwater flow, in Flow Through Porous Media (Academic Press, New York, 1969)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Ling, H., Samarasinghe, S., Kulasiri, D. (2016). Stochastic Neural Networks for Modelling Random Processes from Observed Data. In: Shanmuganathan, S., Samarasinghe, S. (eds) Artificial Neural Network Modelling. Studies in Computational Intelligence, vol 628. Springer, Cham. https://doi.org/10.1007/978-3-319-28495-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-28495-8_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-28493-4
Online ISBN: 978-3-319-28495-8
eBook Packages: EngineeringEngineering (R0)