Approximation of nonlinear functionals using deep ReLU networks
From MaRDI portal
Abstract: In recent years, functional neural networks have been proposed and studied in order to approximate nonlinear continuous functionals defined on for integers and . However, their theoretical properties are largely unknown beyond universality of approximation or the existing analysis does not apply to the rectified linear unit (ReLU) activation function. To fill in this void, we investigate here the approximation power of functional deep neural networks associated with the ReLU activation function by constructing a continuous piecewise linear interpolation under a simple triangulation. In addition, we establish rates of approximation of the proposed functional deep ReLU networks under mild regularity conditions. Finally, our study may also shed some light on the understanding of functional data learning algorithms.
Cites work
- Approximating functions with multi-features by deep convolutional neural networks
- Approximation by Combinations of ReLU and Squared ReLU Ridge Functions With <inline-formula> <tex-math notation="LaTeX">$\ell^1$ </tex-math> </inline-formula> and <inline-formula>
- Approximation by superpositions of a sigmoidal function
- Approximation properties of a multilayered feedforward artificial neural network
- Deep distributed convolutional neural networks: universality
- Error bounds for approximations with deep ReLU networks
- Functional data analysis
- Functional multi-layer perceptron: A nonlinear tool for functional data analysis
- scientific article; zbMATH DE number 3246460 (Why is no real title available?)
- scientific article; zbMATH DE number 3191390 (Why is no real title available?)
- scientific article; zbMATH DE number 3080734 (Why is no real title available?)
- Limitations of the approximation capabilities of neural networks with one hidden layer
- Multilayer feedforward networks are universal approximators
- Neural Networks for Functional Approximation and System Identification
- Online gradient descent algorithms for functional data learning
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks
- Provable approximation properties for deep neural networks
- ReLU deep neural networks and linear finite elements
- Universal approximation bounds for superpositions of a sigmoidal function
- Universality of deep convolutional neural networks
Cited in
(18)- Constructive deep ReLU neural network approximation
- Function approximation by deep neural networks with parameters \(\{0, \pm \frac{1}{2}, \pm 1,2\}\)
- Universal approximation with quadratic deep networks
- Function approximation by deep networks
- scientific article; zbMATH DE number 1497356 (Why is no real title available?)
- Approximation by Combinations of ReLU and Squared ReLU Ridge Functions With <inline-formula> <tex-math notation="LaTeX">$\ell^1$ </tex-math> </inline-formula> and <inline-formula> <tex-math notation="LaTeX">$\ell^0$ </tex-math> </inline-formula> Controls
- Approximations with deep neural networks in Sobolev time-space
- Deep ReLU Networks Overcome the Curse of Dimensionality for Generalized Bandlimited Functions
- Deep learning-based approximation of Goldbach partition function
- Approximation in shift-invariant spaces with deep ReLU neural networks
- Approximation of smooth functionals using deep ReLU networks
- On the convergence of gradient descent for robust functional linear regression
- Spectral algorithms for functional linear regression
- Nyström subsampling for functional linear regression
- A simplified Tikhonov regularization for solving a backward advection-dispersion problem
- Learning Fréchet differentiable operators via prespecified neural operators
- Nonlinear functional regression by functional deep neural network with kernel embedding
- Spherical analysis of learning nonlinear functionals
This page was built for publication: Approximation of nonlinear functionals using deep ReLU networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6170363)
