Deep distributed convolutional neural networks: Universality

DOI10.1142/S0219530518500124zbMath1442.68214WikidataQ130124717 ScholiaQ130124717MaRDI QIDQ4560301

Ding-Xuan Zhou

Publication date: 10 December 2018

Published in: Analysis and Applications (Search for Journal in Brave)

zbMATH Keywords

universalityconvolutional neural networksdeep learningdeep distributed convolutional neural networksfilter mask

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items (61)

Compressed data separation via unconstrained l1-split analysis ⋮ A mesh-free method using piecewise deep neural network for elliptic interface problems ⋮ Approximation properties of deep ReLU CNNs ⋮ Modified proximal symmetric ADMMs for multi-block separable convex optimization with linear constraints ⋮ Unnamed Item ⋮ Rates of convergence of randomized Kaczmarz algorithms in Hilbert spaces ⋮ Neural network interpolation operators activated by smooth ramp functions ⋮ Learning rate of distribution regression with dependent samples ⋮ Weighted random sampling and reconstruction in general multivariate trigonometric polynomial spaces ⋮ Distributed semi-supervised regression learning with coefficient regularization ⋮ Theory of deep convolutional neural networks: downsampling ⋮ Theory of deep convolutional neural networks. III: Approximating radial functions ⋮ Approximating smooth and sparse functions by deep neural networks: optimal approximation rates and saturation ⋮ Rates of approximation by ReLU shallow neural networks ⋮ Neural network interpolation operators optimized by Lagrange polynomial ⋮ Probabilistic robustness estimates for feed-forward neural networks ⋮ Learning rates for the kernel regularized regression with a differentiable strongly convex loss ⋮ Approximation by multivariate max-product Kantorovich-type operators and learning rates of least-squares regularized regression ⋮ On the K-functional in learning theory ⋮ Convergence on sequences of Szász-Jakimovski-Leviatan type operators and related results ⋮ Convergence theorems in Orlicz and Bögel continuous functions spaces by means of Kantorovich discrete type sampling operators ⋮ Some new inequalities and numerical results of bivariate Bernstein-type operator including Bézier basis and its GBS operator ⋮ Rate of convergence of Stancu type modified \(q\)-Gamma operators for functions with derivatives of bounded variation ⋮ Error analysis of kernel regularized pairwise learning with a strongly convex loss ⋮ Dunkl analouge of Szász Schurer Beta bivariate operators ⋮ SignReLU neural network and its approximation ability ⋮ Neural network interpolation operators of multivariate functions ⋮ Error bounds for approximations using multichannel deep convolutional neural networks with downsampling ⋮ On Szász-Durrmeyer type modification using Gould Hopper polynomials ⋮ Deep learning theory of distribution regression with CNNs ⋮ Approximation of nonlinear functionals using deep ReLU networks ⋮ Deep learning via dynamical systems: an approximation perspective ⋮ Sketching with Spherical Designs for Noisy Data Fitting on Spheres ⋮ Quadratic Neural Networks for Solving Inverse Problems ⋮ Bias corrected regularization kernel method in ranking ⋮ PhaseMax: Stable guarantees from noisy sub-Gaussian measurements ⋮ Approximation rates for neural networks with general activation functions ⋮ Approximation Properties of Ridge Functions and Extreme Learning Machines ⋮ Unnamed Item ⋮ Optimal learning rates for distribution regression ⋮ Distributed regularized least squares with flexible Gaussian kernels ⋮ Unnamed Item ⋮ Universality of deep convolutional neural networks ⋮ Equivalence of approximation by convolutional neural networks and fully-connected networks ⋮ Online regularized pairwise learning with least squares loss ⋮ Theory of deep convolutional neural networks. II: Spherical analysis ⋮ MgNet: a unified framework of multigrid and convolutional neural network ⋮ Rates of approximation by neural network interpolation operators ⋮ Stochastic Markov gradient descent and training low-bit neural networks ⋮ Deep neural networks for rotation-invariance approximation and learning ⋮ Robust randomized optimization with k nearest neighbors ⋮ Learning under \((1 + \epsilon)\)-moment conditions ⋮ Balanced joint maximum mean discrepancy for deep transfer learning ⋮ On the speed of uniform convergence in Mercer's theorem ⋮ Distributed Filtered Hyperinterpolation for Noisy Data on the Sphere ⋮ Learning rates for partially linear support vector machine in high dimensions ⋮ Approximation by max-product sampling Kantorovich operators with generalized kernels ⋮ Functional linear regression with Huber loss ⋮ Approximation of functions from korobov spaces by deep convolutional neural networks ⋮ Approximating functions with multi-features by deep convolutional neural networks ⋮ Error analysis of the moving least-squares regression learning algorithm with β-mixing and non-identical sampling

Uses Software

• darch

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Consistency analysis of an empirical minimum error entropy algorithm
• Unregularized online learning algorithms with general loss functions
• On best approximation by ridge functions
• Fundamentality of ridge functions
• Why does deep and cheap learning work so well?
• Multilayer feedforward networks are universal approximators
• Approximation properties of a multilayered feedforward artificial neural network
• Limitations of the approximation capabilities of neural networks with one hidden layer
• Deep vs. shallow networks: An approximation theory perspective
• Ten Lectures on Wavelets
• Universal approximation bounds for superpositions of a sigmoidal function
• Neural Networks for Localized Approximation
• Thresholded spectral algorithms for sparse approximations
• Learning theory of distributed spectral algorithms
• A Fast Learning Algorithm for Deep Belief Nets
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Deep distributed convolutional neural networks: Universality