Published in Int. Journal for Numerical Methods in Engineering Vol. 75 (11), pp. 1341-1360, 2008
doi: 10.1002/nme.2304

Abstract

In this work a conceptual theory of neural networks (NNs) from the perspective of functional analysis and variational calculus is presented. Within this formulation, the learning problem for the multilayer perceptron lies in terms of finding a function, which is an extremal for some functional. Therefore, a variational formulation for NNs provides a direct method for the solution of variational problems.
This proposed method is then applied to distinct types of engineering problems. In particular a shape design, an optimal control and an inverse problem are considered. The selected examples can be solved analytically, which enables a fair comparison with the NN results.

D. Maity, F. Aminzadeh, M. Karrenbach. Novel hybrid artificial neural network based autopicking workflow for passive seismic data. Geophysical Prospecting 62(4) (2014) DOI 10.1111/1365-2478.12125

J. Pons-Prats, G. Bugeda, F. Zárate, E. Oñate. Optimización robusta en aplicaciones aeronáuticas con la combinación de cálculo estocástico y algoritmos evolutivos. Revista Internacional de Métodos Numéricos para Cálculo y Diseño en Ingeniería 28(1) DOI 10.1016/j.rimni.2011.11.001

F. Salazar, R. Morán, R. Rossi, E. Oñate. Analysis of the discharge capacity of radial-gated spillways using CFD and ANN – Oliana Dam case study. Journal of Hydraulic Research 51(3) (2013) DOI 10.1080/00221686.2012.755714

M. Dolgopolik. New Direct Numerical Methods for Some Multidimensional Problems of the Calculus of Variations. Numerical Functional Analysis and Optimization 39(4) (2017) DOI 10.1080/01630563.2017.1378231

J. Pons-Prats, G. Bugeda, F. Zárate, E. Oñate. Robust design optimization in aeronautics using stochastic analysis and evolutionary algorithms. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering 225(10) (2011) DOI 10.1177/0954410011412131

P. Dadvand, R. Rossi, E. Oñate. An Object-oriented Environment for Developing Finite Element Codes for Multi-disciplinary Applications. Arch Computat Methods Eng 17(3) (2010) DOI 10.1007/s11831-010-9045-2