Approximation properties of ridge functions and extreme learning machines
From MaRDI portal
(Redirected from Publication:5154637)
Recommendations
- Approximation by Ridge Functions and Neural Networks
- Best approximation by ridge functions in L_p-spaces
- Ridge functions and applications in neural networks
- Approximation by ridge functions and neural networks with a bounded number of neurons
- Approximation by sums of ridge functions with fixed directions
Cites work
- 0n the best approximation by ridge functions in the uniform norm
- A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
- Approximation by neural networks with weights varying on a finite set of directions
- Approximation by Ridge Functions and Neural Networks
- Approximation by sums of ridge functions with fixed directions
- Approximation by superpositions of a sigmoidal function
- Best approximation by ridge functions in L_p-spaces
- Deep distributed convolutional neural networks: universality
- Error bounds for approximation with neural networks
- Fundamentality of ridge functions
- scientific article; zbMATH DE number 47995 (Why is no real title available?)
- scientific article; zbMATH DE number 515978 (Why is no real title available?)
- scientific article; zbMATH DE number 204193 (Why is no real title available?)
- scientific article; zbMATH DE number 3447525 (Why is no real title available?)
- scientific article; zbMATH DE number 1405266 (Why is no real title available?)
- Multilayer feedforward networks are universal approximators
- Non-iterative and fast deep learning: multilayer extreme learning machines
- On best approximation by ridge functions
- Provable approximation properties for deep neural networks
- Ridge functions and orthonormal ridgelets
- Ridge wavelets on the ball
- Universal approximation bounds for superpositions of a sigmoidal function
- Weak compactness and reflexivity
Cited in
(7)- Approximation of curve-based sleeve functions in high dimensions
- Mathematical analysis for interacting multi functional extreme learning machines
- Operator-valued kernels, machine learning, and dynamical systems
- Finding optimal weight vectors for ridge function approximation in L^2(D)
- Mathematical models of functional extreme learning machines: operator-algebraic and free-probabilistic approaches
- Operator theory of multiple Itô-integrals
- New duality in choices of feature spaces via kernel analysis
This page was built for publication: Approximation properties of ridge functions and extreme learning machines
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5154637)
