Neural network integral representations with the ReLU activation function

Learning representations by back-propagating errors

David E Rumelhart, Geoffrey E Hinton, Ronald J Williams, et al · 1988

Earlier work this paper cites.

Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory

Yoshifusa Ito · 1991

Earlier work this paper cites.

Universal approximation bounds for superpositions of a sigmoidal function

Andrew R Barron · 1993

Earlier work this paper cites.

Learning and generalization characteristics of the random vector functional-link net

Yoh-Han Pao, Gwang-Hoon Park, and Dejan J Sobajic · 1994

Earlier work this paper cites.

The functional link net and learning optimal control

Yoh-Han Pao and Stephen M Phillips · 1995

Earlier work this paper cites.

Regularization of inverse problems , volume 375

Heinz Werner Engl, Martin Hanke, and Andreas Neubauer · 1996

Earlier work this paper cites.

Estimates of the number of hidden units and variation with respect to half-spaces

Věra Kůrková, Paul C Kainen, and Vladik Kreinovich · 1997

Earlier work this paper cites.

Harmonic analysis of neural networks

Emmanuel J Candès · 1999

Cited alongside, same era.

Regularization networks and support vector machines

Theodoros Evgeniou, Massimiliano Pontil, and Tomaso Poggio · 2000

Cited alongside, same era.

An integral formula for heaviside neural networks

Paul C Kainen, Věra Kůrková, and Andrew Vogt · 2000

Cited alongside, same era.

On the tractability of multivariate integration and approximation by neural networks

Hrushikesh Narhar Mhaskar · 2004

Cited alongside, same era.

Convex neural networks

Yoshua Bengio, Nicolas L Roux, Pascal Vincent, Olivier Delalleau, and Patrice Marcotte · 2006

Cited alongside, same era.

Integral combinations of heavisides

Paul C Kainen, Věra Kůrková, and Andrew Vogt · 2010

Cited alongside, same era.

Risk bounds for high-dimensional ridge function combinations including neural networks

Original

Jason M Klusowski and Andrew R Barron · 2016

Later among the works it cites.

Breaking the curse of dimensionality with convex neural networks

Francis Bach · 2017

Later among the works it cites.

Why and when can deep-but not shallow-networks avoid the curse of dimensionality: a review

Tomaso Poggio, Hrushikesh Mhaskar, Lorenzo Rosasco, Brando Miranda, and Qianli Liao · 2017

Later among the works it cites.

Neural network with unbounded activation functions is universal approximator

Sho Sonoda and Noboru Murata · 2017

Later among the works it cites.

Barron spaces and the compositional function spaces for neural network models

Original

Chao Ma, Lei Wu, et al · 2019

Closest in time.