Universal Approximation Theorem for Input-Connected Multilayer Perceptrons

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Ismailov, Vugar
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917358943076352
author Ismailov, Vugar
author_facet Ismailov, Vugar
contents We present the Input-Connected Multilayer Perceptron (IC-MLP), a feedforward neural network architecture in which each hidden neuron receives, in addition to the outputs of the preceding layer, a direct affine connection from the raw input. We first study this architecture in the univariate setting and give an explicit and systematic description of IC-MLPs with an arbitrary finite number of hidden layers, including iterated formulas for the network functions. In this setting, we prove a universal approximation theorem showing that deep IC-MLPs can approximate any continuous function on a closed interval of the real line if and only if the activation function is nonlinear. We then extend the analysis to vector-valued inputs and establish a corresponding universal approximation theorem for continuous functions on compact subsets of $\mathbb{R}^n$.
format Preprint
id arxiv_https___arxiv_org_abs_2601_14026
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Universal Approximation Theorem for Input-Connected Multilayer Perceptrons
Ismailov, Vugar
Machine Learning
Neural and Evolutionary Computing
Functional Analysis
We present the Input-Connected Multilayer Perceptron (IC-MLP), a feedforward neural network architecture in which each hidden neuron receives, in addition to the outputs of the preceding layer, a direct affine connection from the raw input. We first study this architecture in the univariate setting and give an explicit and systematic description of IC-MLPs with an arbitrary finite number of hidden layers, including iterated formulas for the network functions. In this setting, we prove a universal approximation theorem showing that deep IC-MLPs can approximate any continuous function on a closed interval of the real line if and only if the activation function is nonlinear. We then extend the analysis to vector-valued inputs and establish a corresponding universal approximation theorem for continuous functions on compact subsets of $\mathbb{R}^n$.
title Universal Approximation Theorem for Input-Connected Multilayer Perceptrons
topic Machine Learning
Neural and Evolutionary Computing
Functional Analysis
url https://arxiv.org/abs/2601.14026