Integral representations of shallow neural network with Rectified Power Unit activation function
Not on the map. Why?
Abstract (arXiv)
In this effort, we derive a formula for the integral representation of a shallow neural network with the Rectified Power Unit activation function. Mainly, our first result deals with the univariate case of representation capability of RePU shallow networks. The multidimensional result in this paper characterizes the set of functions that can be represented with bounded norm and possibly unbounded width.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 21 of its 45 references that are in the map. First posted on arXiv 20 Dec 2021.
Builds on
21 of 45 references.
References · 21
- 2016Error bounds for approximations with deep ReLU networkscited by 567
- 2017Nonparametric regression using deep neural networks with ReLU activation functioncited by 431
- 2014In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learningcited by 339
- 2015Norm-Based Capacity Control in Neural Networkscited by 299
- 2020Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Losscited by 267
- 2016Benefits of depth in neural networkscited by 248
- 2015The Power of Depth for Feedforward Neural Networkscited by 181
- 2018Regularization Matters: Generalization and Optimization of Neural Nets v.s. their Induced Kernelcited by 131
- 2019A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Casecited by 113
- 2019How do infinite width bounded norm networks look in function space?cited by 105
- 2020Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networkscited by 96
- 2019Deep Neural Network Approximation Theorycited by 92
9 more
- 2017Optimal Approximation with Sparsely Connected Deep Neural Networkscited by 90
- 2020Representation formulas and pointwise properties for Barron functionscited by 62
- 2019Lexicographic and Depth-Sensitive Margins in Homogeneous and Non-Homogeneous Deep Modelscited by 53
- 2019Approximation spaces of deep neural networkscited by 51
- 2019Neural tangent kernels, transportation mappings, and universal approximationcited by 30
- 2020Neural network approximation and estimation of classifiers with classification boundary in a Barron classcited by 28
- 2021Two-layer neural networks with values in a Banach spacecited by 26
- 2020Approximations with deep neural networks in Sobolev time-spacecited by 13
- 2019Neural network integral representations with the ReLU activation functioncited by 8
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.