A concentration result for multilayer feedforward neural networks
Abstract
We consider for an arbitrary fixed ρ and for each positive integer n a multilayer feedforward artificial neural network with ρ layers, n neurons in the first layer (the input layer) and only one neuron, the output neuron, in the last layer. Very roughly formulated, the main result is that if the distribution of weights of connections from a layer to the next are, for all large n, approximated well by a fixed continuous (but otherwise arbitrary) curve which does not depend on n, and if the values of the n input neurons are independently and identically distributed with a continuous probability density function, then there is a number ψ such that for all ε > 0 the probability that the value of the output neuron is in [ψ− ε, ψ+ ε] tends to 1 as n tends to infinity.
Related
- Informative Fisher Modes in Neural Networks as a Result of Explicit Symmetry Breaking
- A Class of Rényi-based Concentration Metrics for Kolmogorov-Arnold Geometry in Multilayer Perceptrons
- A latent space hidden Markov model for clustering views in longitudinal multilayer networks
- Double explosive transitions in adaptive multilayer networks with higher-order interactions
- Fraud Detection via Bayesian Positive-Unlabeled Learning with Gaussian Processes and Multilayer Networks
BibTeX
@misc{koponen2026concentration,
title = {{A concentration result for multilayer feedforward neural networks}},
author = {Vera Koponen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.15335},
eprint = {2608.15335},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.15335},
}
RIS
TY - UNPB
TI - A concentration result for multilayer feedforward neural networks
AU - Vera Koponen
PY - 2026
DA - 2026/09/08
PB - arXiv
DO - 10.48550/arxiv.2608.15335
UR - https://arxiv.org/abs/2608.15335
AB - We consider for an arbitrary fixed ρ and for each positive integer n a multilayer feedforward artificial neural network with ρ layers, n neurons in the first layer (the input layer) and only one neuron, the output neuron, in the last layer. Very roughly formulated, the main result is that if the distribution of weights of connections from a layer to the next are, for all large n, approximated well by a fixed continuous (but otherwise arbitrary) curve which does not depend on n, and if the values of the n input neurons are independently and identically distributed with a continuous probability density function, then there is a number ψ such that for all ε > 0 the probability that the value of the output neuron is in [ψ− ε, ψ+ ε] tends to 1 as n tends to infinity.
ER -