Published in ICANN 2006, S. Kollias et al (Eds.), ICANN 2006, Part I, LNCS 4131, pp. 19-168, Germany, 2006
DOI: 10.1007/11840817_17

Abstract

In this work we present a theory of the multilayer perceptron from the perspective of functional analysis and variational calculus. Within this formulation, the learning problem for the multilayer perceptron lies in terms of finding a function which is an extremal for some functional. As we will see, a variational formulation for the multilayer perceptron provides a direct method for the solution of general variational problems, in any dimension and up to any degree of accuracy. In order to validate this technique we use a multilayer perceptron to solve some classical problems in the calculus of variations.

A. Amuthan, P. Harikrishna. Mean Availability Parameter-Based DDoS Detection Mechanism for Cloud Computing Environments. (2018) DOI 10.1007/978-981-10-8663-2_12

R. Lopez, E. Balsa-Canto, E. Oñate. Neural networks for variational problems in engineering. Int. J. Numer. Meth. Engng 75(11) DOI 10.1002/nme.2304

M. Khorshed, A. Ali, S. Wasimi. Classifying different denial-of-service attacks in cloud computing using rule-based learning. Security Comm. Networks (2012) DOI 10.1002/sec.621

J. Pons-Prats, E. Oñate, F. Zárate, G. Bugeda, J. Hurtado. Non-Deterministic Shape Optimization in Aeronautics. (2012) DOI 10.2514/6.2008-5827

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