scientific article; zbMATH DE number 7387622
From MaRDI portal
Publication:5011561
DOI10.11329/JJSSJ.50.285MaRDI QIDQ5011561FDOQ5011561
Authors: Sho Sonoda 
Publication date: 27 August 2021
Title of this publication is not available (Why is that?)
Cites Work
- A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
- Universal approximation bounds for superpositions of a sigmoidal function
- Support Vector Machines
- High-dimensional probability. An introduction with applications in data science
- On the equivalence between kernel quadrature rules and random feature expansions
- Title not available (Why is that?)
- Classical Fourier Analysis
- 10.1162/153244303321897690
- Title not available (Why is that?)
- The ridgelet transform of distributions
- Bayesian learning for neural networks
- Integral geometry and Radon transforms
- The Calderón reproducing formula, windowed \(X\)-ray transforms, and Radon transforms in \(L^p\)-spaces
- Title not available (Why is that?)
- Inverse Radon transforms through inverse wavelet transforms
- Complexity estimates based on integral transforms induced by computational units
- Title not available (Why is that?)
- Error bounds for approximations with deep ReLU networks
- Stable architectures for deep neural networks
- Mean field analysis of neural networks: a central limit theorem
- Neural network with unbounded activation functions is universal approximator
- A proposal on machine learning via dynamical systems
- Maximum principle based algorithms for deep learning
- A mean field view of the landscape of two-layer neural networks
- A representer theorem for deep neural networks
- Mean field analysis of neural networks: a law of large numbers
- Transport analysis of infinitely deep neural network
Uses Software
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5011561)
