English
Related papers

Related papers: Sigmoidal approximations of a nonautonomous neural…

200 papers

We prove a negative result for the approximation of functions defined on compact subsets of $\mathbb{R}^d$ (where $d \geq 2$) using feedforward neural networks with one hidden layer and arbitrary continuous activation function. In a…

Machine Learning · Computer Science 2020-08-26 J. M. Almira , P. E. Lopez-de-Teruel , D. J. Romero-Lopez , F. Voigtlaender

Superposition of sigmoid function over a finite time interval is shown to be equivalent to the linear combination of the solutions of a linearly parameterized system of logistic differential equations. Due to the linearity with respect to…

Optimization and Control · Mathematics 2016-09-07 Ivan Tyukin , Cees van Leeuwen , Danil Prokhorov

The connection between Bayesian neural networks and Gaussian processes gained a lot of attention in the last few years, with the flagship result that hidden units converge to a Gaussian process limit when the layers width tends to infinity.…

Machine Learning · Statistics 2021-11-30 Mariia Vladimirova , Julyan Arbel , Stéphane Girard

In the present article, we introduce and study the behaviour of the new family of exponential type neural network operators activated by the sigmoidal functions. We establish the point-wise and uniform approximation theorems for these NN…

Numerical Analysis · Mathematics 2019-11-14 S. Bajpeyi , A. Sathish Kumar

To better understand complexity in neural networks, we theoretically investigate the idealised phenomenon of lossless network compressibility, whereby an identical function can be implemented with fewer hidden units. In the setting of…

Machine Learning · Computer Science 2024-05-27 Matthew Farrugia-Roberts

We provide general adaptive upper bounds for estimating nonparametric functionals based on second order U-statistics arising from finite dimensional approximation of the infinite dimensional models. We then provide examples of functionals…

Statistics Theory · Mathematics 2021-06-07 Lin Liu , Rajarshi Mukherjee , James Robins , Eric Tchetgen Tchetgen

In linear models, visualizing a weight vector naturally reveals the model's preferred input direction, but extending this intuition to deep networks via gradients or gradient ascent often yields brittle or adversarial-looking features. We…

Machine Learning · Computer Science 2026-05-08 Maciej Satkiewicz , Roberto Corizzo , Marcin Pietroń

We adapt previous research on category theory and topological unsupervised learning to develop a functorial perspective on manifold learning, also known as nonlinear dimensionality reduction. We first characterize manifold learning…

Machine Learning · Computer Science 2022-11-04 Dan Shiebler

The second and third authors of this paper have constructed in [14] finite-dimensional attractors for the one-dimensional Keller-Segel equations. They have also remarked in [14, Section 7] that, when the sensitivity function is a linear…

Analysis of PDEs · Mathematics 2020-09-08 Satoru Iwasaki , Koichi Osaki , Atsushi Yagi

By developing new efficient techniques and using an appropriate fixed point theorem, we derive several new sufficient conditions for the pseudo almost periodic solutions with double measure for some system of differential equations with…

Analysis of PDEs · Mathematics 2020-03-11 Mohsen Miraoui , Dušan D. Repovš

In this paper, we consider the nonparametric random regression model $Y=f_1(X_1)+f_2(X_2)+\epsilon$ and address the problem of estimating the function $f_1$. The term $f_2(X_2)$ is regarded as a nuisance term which can be considerably more…

Statistics Theory · Mathematics 2015-02-03 Martin Wahl

We provide a systematic investigation of using physics-informed neural networks to compute Lyapunov functions. We encode Lyapunov conditions as a partial differential equation (PDE) and use this for training neural network Lyapunov…

Optimization and Control · Mathematics 2025-06-04 Jun Liu , Yiming Meng , Maxwell Fitzsimmons , Ruikun Zhou

We study the implicit bias of the general family of steepest descent algorithms with infinitesimal learning rate in deep homogeneous neural networks. We show that: (a) an algorithm-dependent geometric margin starts increasing once the…

Machine Learning · Computer Science 2025-09-23 Nikolaos Tsilivis , Eitan Gronich , Julia Kempe , Gal Vardi

The goal of a recommendation system is to predict the interest of a user in a given item by exploiting the existing set of ratings as well as certain user/item features. A standard approach to modeling this problem is Inductive Matrix…

Machine Learning · Computer Science 2018-05-29 Kai Zhong , Zhao Song , Prateek Jain , Inderjit S. Dhillon

Currently, deep neural networks are the state of the art on problems such as speech recognition and computer vision. In this extended abstract, we show that shallow feed-forward networks can learn the complex functions previously learned by…

Machine Learning · Computer Science 2014-10-14 Lei Jimmy Ba , Rich Caruana

A broad range of inverse problems can be abstracted into the problem of minimizing the sum of several convex functions in a Hilbert space. We propose a proximal decomposition algorithm for solving this problem with an arbitrary number of…

Optimization and Control · Mathematics 2009-11-13 Patrick L. Combettes , Jean-Christophe Pesquet

Functions correspond to one of the key concepts in mathematics and science, allowing the representation and modeling of several types of signals and systems. The present work develops an approach for characterizing the coverage and…

Discrete Mathematics · Computer Science 2021-02-08 Luciano da F. Costa

This article is concerned with the approximation and expressive powers of deep neural networks. This is an active research area currently producing many interesting papers. The results most commonly found in the literature prove that neural…

Machine Learning · Computer Science 2019-05-08 I. Daubechies , R. DeVore , S. Foucart , B. Hanin , G. Petrova

We extend a recently introduced class of exactly solvable models for recurrent neural networks with competition between 1D nearest neighbour and infinite range information processing. We increase the potential for further frustration and…

Disordered Systems and Neural Networks · Physics 2009-10-31 N. S. Skantzos , A. C. C. Coolen

We establish in this work approximation results of deep neural networks for smooth functions measured in Sobolev norms, motivated by recent development of numerical solvers for partial differential equations using deep neural networks. {Our…

Numerical Analysis · Mathematics 2022-07-25 Sean Hon , Haizhao Yang