Approximation Properties of Ridge Functions and Extreme Learning Machines
From MaRDI portal
Publication:5154637
DOI10.1137/20M1356348zbMath1487.41029MaRDI QIDQ5154637
Palle E. T. Jorgensen, David E. Stewart
Publication date: 5 October 2021
Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)
Related Items (1)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Approximation by neural networks with weights varying on a finite set of directions
- A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
- On best approximation by ridge functions
- Fundamentality of ridge functions
- Multilayer feedforward networks are universal approximators
- Provable approximation properties for deep neural networks
- Non-iterative and fast deep learning: multilayer extreme learning machines
- Weak compactness and reflexivity
- Ridge wavelets on the ball
- Best approximation by ridge functions in L p -spaces
- Approximation by Ridge Functions and Neural Networks
- Universal approximation bounds for superpositions of a sigmoidal function
- Deep distributed convolutional neural networks: Universality
- Approximation by sums of ridge functions with fixed directions
- Approximation by superpositions of a sigmoidal function
- Ridge functions and orthonormal ridgelets
- 0n the best approximation by ridge functions in the uniform norm
- Error bounds for approximation with neural networks
This page was built for publication: Approximation Properties of Ridge Functions and Extreme Learning Machines
