Two-hidden-layer feed-forward networks are universal approximators: a constructive approach

DOI10.1016/J.NEUNET.2020.07.021MaRDI QIDQ2057712zbMATH OpenOpenAlexDBLPWikidataFDO

Authors Eduardo Paluzo-Hidalgo, Rocío González-Díaz, Miguel A. Gutiérrez-Naranjo

Publication date 7 December 2021

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1907.11457

zbMATH Keywords

multi-layer feed-forward networksimplicial approximation theoremtriangulationsuniversal approximation theorem

Mathematics Subject Classification ID

Approximation by other special function classes (41A30) Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Abstract: It is well known that Artificial Neural Networks are universal approximators. The classical result proves that, given a continuous function on a compact set on an n-dimensional space, then there exists a one-hidden-layer feedforward network which approximates the function. Such result proves the existence, but it does not provide a method for finding it. In this paper, a constructive approach to the proof of this property is given for the case of two-hidden-layer feedforward networks. This approach is based on an approximation of continuous functions by simplicial maps. Once a triangulation of the space is given, a concrete architecture and set of weights can be obtained. The quality of the approximation depends on the refinement of the covering of the space by simplicial complexes.

Recommendations

• Multilayer feedforward networks are universal approximators
• Approximation properties of some two-layer feedforward neural networks
• On the approximation by neural networks with bounded number of neurons in hidden layers
• Neural networks for optimal approximation of continuous functions in \(\mathbb R^d\)
• The universal approximation capabilities of cylindrical approximate identity neural networks

Cites work

• Approximation by superpositions of a sigmoidal function
• Computational topology. An introduction
• Geometric and topological inference
• scientific article; zbMATH DE number 4102053 (Why is no real title available?)
• scientific article; zbMATH DE number 2103273 (Why is no real title available?)
• scientific article; zbMATH DE number 1392848 (Why is no real title available?)
• Multilayer feedforward networks are universal approximators
• On the approximation by single hidden layer feedforward neural networks with fixed weights

Cited in

(8)

• A class of universal approximators of real continuous functions revisited
• The universal approximation capabilities of cylindrical approximate identity neural networks
• Multilayer feedforward networks are universal approximators
• Function approximation on non-Euclidean spaces
• scientific article; zbMATH DE number 541483 (Why is no real title available?)
• The generalized extreme learning machines: tuning hyperparameters and limiting approach for the Moore-Penrose generalized inverse
• Trainable and explainable simplicial map neural networks
• Data-driven approach for estimating longitudinal aerodynamic parameters using neural artificial bee colony fusion algorithm

This page was built for publication: Two-hidden-layer feed-forward networks are universal approximators: a constructive approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2057712)