paper-with-me

Papers

Geometric separation and constructive universal approximation with two hidden layers

2026-02-12 · Chanyoung Sung arxiv

We give a geometric construction of neural networks that separate disjoint compact subsets of $\Bbb R^n$, and use it to obtain a constructive universal approximation theorem. Specifically, we show that networks with two hidden layers and either a sigmoidal activation (i.e., strictly monotone bounded continuous) or the ReLU activation can approximate any real-valued continuous function on an arbitrary compact set $K\subset\Bbb R^n$ to any prescribed accuracy in the uniform norm. For finite $K$, the construction simplifies and yields a sharp depth-2 (single hidden layer) approximation result.

📄 PDF Abstract BibTeX arXiv:2602.12482

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Two-hidden-layer Feedforward Neural Networks are Universal Approximators: A Constructive Approach

2019-07-26 · Rocio Gonzalez-Diaz, Miguel A. Gutiérrez-Naranjo, Eduardo Paluzo-Hidalgo

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…

Universal Approximation Theorems of Fully Connected Binarized Neural Networks

2021-02-04 · Mikail Yayla, Mario Günzel, Burim Ramosaj, Jian-Jia Chen

Neural networks (NNs) are known for their high predictive accuracy in complex learning problems. Beside practical advantages, NNs also indicate favourable theoretical properties such as universal approximation (UA) theor…

LightGCNet: A Lightweight Geometric Constructive Neural Network for Data-Driven Soft sensors

2023-12-19 · Jing Nan, Yan Qin, Wei Dai, Chau Yuen

Data-driven soft sensors provide a potentially cost-effective and more accurate modeling approach to measure difficult-to-measure indices in industrial processes compared to mechanistic approaches. Artificial intelligenc…

On the approximation by single hidden layer feedforward neural networks with fixed weights

2017-08-21 · Namig J. Guliyev, Vugar E. Ismailov

Feedforward neural networks have wide applicability in various disciplines of science due to their universal approximation property. Some authors have shown that single hidden layer feedforward neural networks (SLFNs) wi…

Simplicial Neural Networks:First Steps and Future Applications

2020-10-10 · Anonymous

It is well-known that artificial neural networks are universal approximators. The Universal Approximation Theorem proves that, given a continuous function on a compact set embedded in an $n$-dimensional space, there exis…