Approximating the Algebraic Solution of System of Interval Linear Equations with Use of Neural Networks
A new approach to approximate the algebraic solution of systems of interval linear equations (SILE) is proposed in this paper. The original SILE problem is first transformed into an optimization problem, which is in turn solved with use of artificial neural networks and gradient-based optimization techniques.
KeywordsCost Function Hide Neuron Interval Arithmetic Interval Number Algebraic Solution
Unable to display preview. Download preview PDF.
- G. Alefeld, J. Herzberger, Introduction to Interval Computation, Academic Press, London, 1983Google Scholar
- L.T. Fine, Feedforward Neural Network Methodology, Springer-Verlag: New York, 1999Google Scholar
- F.M Ham, I. Kostanic, Principles of Neurocom-puting for Science and Engineering, McGraw-Hill Education-Europe 2001Google Scholar
- L. Jaulin, M. Kieffer, O. Didrit, E. Walter, Applied Interval Analysis, Springer-Verlag, London 2001Google Scholar
- A. Neumaier, Interval Methods for Systems of Linear Equations, Cambridge University Press, 1990Google Scholar