Approximation rates for neural networks with encodable weights in smoothness spaces
Published 2020 View Full Article
- Home
- Publications
- Publication Search
- Publication Details
Title
Approximation rates for neural networks with encodable weights in smoothness spaces
Authors
Keywords
Neural networks, Expressivity, Approximation rates, Smoothness spaces, Encodable weights
Journal
NEURAL NETWORKS
Volume 134, Issue -, Pages 107-130
Publisher
Elsevier BV
Online
2020-11-28
DOI
10.1016/j.neunet.2020.11.010
References
Ask authors/readers for more resources
Related references
Note: Only part of the references are listed.- Machine Learning Approximation Algorithms for High-Dimensional Fully Nonlinear Partial Differential Equations and Second-order Backward Stochastic Differential Equations
- (2019) Christian Beck et al. JOURNAL OF NONLINEAR SCIENCE
- Convergence in Orlicz spaces by means of the multivariate max-product neural network operators of the Kantorovich type and applications
- (2019) Danilo Costarelli et al. NEURAL COMPUTING & APPLICATIONS
- Smooth Function Approximation by Deep Neural Networks with General Activation Functions
- (2019) Ilsang Ohn et al. Entropy
- Error bounds for approximations with deep ReLU neural networks in Ws,p norms
- (2019) Ingo Gühring et al. Analysis and Applications
- Deep ReLU networks and high-order finite element methods
- (2019) Joost A. A. Opschoor et al. Analysis and Applications
- Better Approximations of High Dimensional Smooth Functions by Deep Neural Networks with Rectified Power Units
- (2019) Bo Li Communications in Computational Physics
- Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ
- (2018) Christoph Schwab et al. Analysis and Applications
- Provable approximation properties for deep neural networks
- (2018) Uri Shaham et al. APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS
- DGM: A deep learning algorithm for solving partial differential equations
- (2018) Justin Sirignano et al. JOURNAL OF COMPUTATIONAL PHYSICS
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks
- (2018) Philipp Petersen et al. NEURAL NETWORKS
- Approximation capability of two hidden layer feedforward neural networks with fixed weights
- (2018) Namig J. Guliyev et al. NEUROCOMPUTING
- Solving high-dimensional partial differential equations using deep learning
- (2018) Jiequn Han et al. PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
- Generalization and Expressivity for Deep Nets
- (2018) Shao-Bo Lin IEEE Transactions on Neural Networks and Learning Systems
- Error bounds for approximations with deep ReLU networks
- (2017) Dmitry Yarotsky NEURAL NETWORKS
- A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate Function
- (2016) Namig J. Guliyev et al. NEURAL COMPUTATION
- Multivariate neural network operators with sigmoidal activation functions
- (2013) Danilo Costarelli et al. NEURAL NETWORKS
- Approximation results for neural network operators activated by sigmoidal functions
- (2013) Danilo Costarelli et al. NEURAL NETWORKS
Discover Peeref hubs
Discuss science. Find collaborators. Network.
Join a conversationCreate your own webinar
Interested in hosting your own webinar? Check the schedule and propose your idea to the Peeref Content Team.
Create Now