Pages that link to "Item:Q1886595"
From MaRDI portal
The following pages link to When is approximation by Gaussian networks necessarily a linear process? (Q1886595):
Displaying 17 items.
- Interpolation and rates of convergence for a class of neural networks (Q840184) (← links)
- Oscillation of Fourier transforms and Markov-Bernstein inequalities (Q872000) (← links)
- Comparing fixed and variable-width Gaussian networks (Q889280) (← links)
- Eignets for function approximation on manifolds (Q984660) (← links)
- Complexity of Gaussian-radial-basis networks approximating smooth functions (Q998978) (← links)
- A tribute to Géza Freud (Q1433342) (← links)
- Applied harmonic analysis and data processing. Abstracts from the workshop held March 25--31, 2018 (Q1731982) (← links)
- The rate of approximation of Gaussian radial basis neural networks in continuous function space (Q1940856) (← links)
- A direct approach for function approximation on data defined manifolds (Q2057766) (← links)
- Approximation of Sobolev classes by polynomials and ridge functions (Q2389529) (← links)
- Two fast and accurate heuristic RBF learning rules for data classification (Q2418116) (← links)
- Deep vs. shallow networks: an approximation theory perspective (Q2835988) (← links)
- Constructive approximation by Gaussian neural networks (Q2871205) (← links)
- George Lorentz and inequalities in approximation (Q3586755) (← links)
- Deep Nitsche Method: Deep Ritz Method with Essential Boundary Conditions (Q5163229) (← links)
- Deep neural networks for rotation-invariance approximation and learning (Q5236745) (← links)
- Applications of classical approximation theory to periodic basis function networks and computational harmonic analysis (Q5396581) (← links)
