Paluzo Hidalgo, EduardoGonzález Díaz, RocíoGutiérrez Naranjo, Miguel Ángel2023-04-032023-04-032020-11Paluzo Hidalgo, E., González Díaz, R. y Gutiérrez Naranjo, M.Á. (2020). Two-hidden-layer feed-forward networks are universal approximators: A constructive approach. Neural Networks, 131, 29-36. https://doi.org/10.1016/j.neunet.2020.07.021.0893-6080 (impreso)1879-2782 (online)https://hdl.handle.net/11441/143874It is well-known that artificial neural networks are universal approximators. The classical existence result proves that, given a continuous function on a compact set embedded in an n-dimensional space, there exists a one-hidden-layer feed-forward network that approximates the function. In this paper, a constructive approach to this problem is given for the case of a continuous function on triangulated spaces. Once a triangulation of the space is given, a two-hidden-layer feed-forward network with a concrete set of weights is computed. The level of the approximation depends on the refinement of the triangulation.application/pdf8engAttribution-NonCommercial-NoDerivatives 4.0 Internacionalhttp://creativecommons.org/licenses/by-nc-nd/4.0/Universal Approximation TheoremSimplicial Approximation TheoremMulti-layer feed-forward networkTriangulationsinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/openAccesshttps://doi.org/10.1016/j.neunet.2020.07.021