A convergent Deep Learning algorithm for approximation of polynomials
We start from the contractive functional equation proposed in [4], where it was shown that the polynomial solution of functional equation can be used to initialize a Neural Network structure, with a controlled accuracy. We propose a novel algorithm, where the functional equation is solved with a con...
Saved in:
Main Author: | Després, Bruno |
---|---|
Format: | Article |
Language: | English |
Published: |
Académie des sciences
2023-09-01
|
Series: | Comptes Rendus. Mathématique |
Online Access: | https://comptes-rendus.academie-sciences.fr/mathematique/articles/10.5802/crmath.462/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Methodics of teaching polynomial approximation of functions in CAS enviroment
by: Vilija Dabrišienė, et al.
Published: (2023-09-01) -
Approximation Bounds for Model Reduction on Polynomially Mapped Manifolds
by: Buchfink, Patrick, et al.
Published: (2024-12-01) -
Solving an inverse Cauchy Problem for modified Helmholtz Equations depending on a polynomial expansion approximation
by: shaimaa aamer, et al.
Published: (2025-01-01) -
Diagnosis of oral cancer using deep learning algorithms
by: Mayra Alejandra Dávila Olivos, et al.
Published: (2024-10-01) -
Adaptive temporal-difference learning via deep neural network function approximation: a non-asymptotic analysis
by: Guoyong Wang, et al.
Published: (2025-01-01)