Universal approximation bounds for superpositions of a sigmoidal function
From MaRDI portal
(Redirected from Publication:4277151)
Recommendations
- Approximation by superpositions of a sigmoidal function
- Approximation and estimation bounds for artificial neural networks
- Estimation of approximating rate for neural network in \(L^p_w\) spaces
- Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives
- Approximation Capability of Layered Neural Networks with Sigmoid Units on Two Layers
Cited in
(only showing first 100 items - show all)- Spectral Barron space for deep neural network approximation
- Modelling the dynamics of nonlinear time series using canonical variate analysis
- Limitations of the approximation capabilities of neural networks with one hidden layer
- Semi-nonparametric approximation and index options
- A class \(+1\) sigmoidal activation functions for FFANNs
- Approximation by superpositions of a sigmoidal function
- Optimal approximation of piecewise smooth functions using deep ReLU neural networks
- A duality framework for analyzing random feature and two-layer neural networks
- Optimal transport map estimation in general function spaces
- The construction and approximation of ReLU neural network operators
- On greedy approximation in complex Banach spaces
- Non intrusive reduced order modeling of parametrized PDEs by kernel POD and neural networks
- Posterior concentrations of fully-connected Bayesian neural networks with general priors on the weights
- Complete stability analysis of a heuristic approximate dynamic programming control design
- Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ
- EO-MTRNN: evolutionary optimization of hyperparameters for a neuro-inspired computational model of spatiotemporal learning
- Fast construction of correcting ensembles for legacy artificial intelligence systems: algorithms and a case study
- Deep ReLU network expression rates for option prices in high-dimensional, exponential Lévy models
- Randomized neural operator for parametric PDEs with fast training and conformal uncertainty quantification
- Path relinking and GRG for artificial neural networks
- Neural network-based variational methods for solving quadratic porous medium equations in high dimensions
- Approximation of Analytic Functions by ReLU Neural Networks with Adjustable Depth and Width
- Full error analysis for the training of deep neural networks
- A mixed residual method for biharmonic equations in spectral Barron spaces
- Elliptic Regularity Theory in Barron Spaces and Applications to the Deep Ritz Method
- Training-Free Universal Approximation by Prompting Random Transformers
- Universal Features for High-Dimensional Learning and Inference
- SignReLU neural network and its approximation ability
- Optimal approximation with sparsely connected deep neural networks
- A methodology for the constructive approximation of nonlinear operators defined on noncompact sets
- Automatic differentiation is essential in training neural networks for solving differential equations
- Integral combinations of Heavisides
- Approximation with random bases: pro et contra
- Insights into randomized algorithms for neural networks: practical issues and common pitfalls
- Universality of deep convolutional neural networks
- A machine learning framework for data driven acceleration of computations of differential equations
- A mathematical explanation of UNet
- Approximation Capability of Layered Neural Networks with Sigmoid Units on Two Layers
- Designing neural networks for modeling biological data: a statistical perspective
- Greedy approximation in convex optimization
- A hybrid iterative method for elliptic variational inequalities of the second kind
- Point cloud neural operator for parametric PDEs on complex and variable geometries
- Non-equilibrium dynamics in complex networks via asymmetric Glauber models
- Embedding inequalities for Barron-type spaces
- RNN-attention based deep learning for solving inverse boundary problems in nonlinear Marshak waves
- A brief survey on the approximation theory for sequence modelling
- Approximation of functionals by neural network without curse of dimensionality
- A priori estimates for deep residual network in continuous-time reinforcement learning
- Greedy algorithms for prediction
- Correlations of random classifiers on large data sets
- Schwarz iterative methods: infinite space splittings
- Standard representation and unified stability analysis for dynamic artificial neural network models
- Optimal deep neural networks by maximization of the approximation power
- scientific article; zbMATH DE number 1843047 (Why is no real title available?)
- Optimization based on quasi-Monte Carlo sampling to design state estimators for non-linear systems
- A phase transition for finding needles in nonlinear haystacks with LASSO artificial neural networks
- Generalization bounds for sparse random feature expansions
- Understanding neural networks with reproducing kernel Banach spaces
- Restricted polynomial regression
- DNN expression rate analysis of high-dimensional PDEs: application to option pricing
- Machine learning from a continuous viewpoint. I
- Approximation of discontinuous signals by sampling Kantorovich series
- Boosting the margin: a new explanation for the effectiveness of voting methods
- Minimizing sequences for a family of functional optimal estimation problems
- Error bounds for approximations using multichannel deep convolutional neural networks with downsampling
- Analysis of the rate of convergence of an over-parametrized convolutional neural network image classifier learned by gradient descent
- Deep learning theory of distribution regression with CNNs
- Information preservation with Wasserstein autoencoders: generation consistency and adversarial robustness
- Consistency and rate of convergence for deep ReLU neural networks
- Efficient sampling in approximate dynamic programming algorithms
- Exponential convergence of the deep neural network approximation for analytic functions
- Nonparametric regression using deep neural networks with ReLU activation function
- Convergence rates for shallow neural networks learned by gradient descent
- Deep Neural Networks for Solving Large Linear Systems Arising from High-Dimensional Problems
- Robust control of dynamical systems using neural networks with input–output feedback linearization
- A mathematical perspective on transformers
- Duality for neural networks through reproducing kernel Banach spaces
- Stability estimate and the Tikhonov regularization method for the Kuramoto-Sivashinsky equation backward in time
- Universality of reservoir systems with recurrent neural networks
- Predictive neuro-control of uncertain systems: Design and use of a neuro-optimizer
- Deep neural network expressivity for optimal stopping problems
- Function approximation with zonal function networks with activation functions analogous to the rectified linear unit functions
- Approximate models for nonlinear dynamical systems and their generalization properties
- Generative Multi-Purpose Sampler for Weighted M-estimation
- The plane wave method for inverse problems associated with Helmholtz-type equations
- Gauss Newton method for solving variational problems of PDEs with neural network discretizaitons
- Two-Layer Neural Networks with Values in a Banach Space
- Can dictionary-based computational models outperform the best linear ones?
- New insights into Witsenhausen's counterexample
- A survey on universal approximation and its limits in soft computing techniques.
- Do ideas have shape? Idea registration as the continuous limit of artificial neural networks
- Representation formulas and pointwise properties for Barron functions
- A nonoverlapping domain decomposition method for extreme learning machines: elliptic problems
- Analysis of the rate of convergence of fully connected deep neural network regression estimates with smooth activation function
- N-adaptive Ritz method: a neural network enriched partition of unity for boundary value problems
- Geometric Rates of Approximation by Neural Networks
- Instability, complexity, and evolution
- MgNet: a unified framework of multigrid and convolutional neural network
- On the curse of dimensionality in the Ritz method
- Learning semidefinite regularizers
This page was built for publication: Universal approximation bounds for superpositions of a sigmoidal function
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4277151)
