Growing axons: greedy learning of neural networks with application to function approximation

DOI10.1515/RNAM-2023-0001OpenAlexW2981405625MaRDI QIDQ2689211

Daria Fokina, Ivan V. Oseledets

Publication date: 9 March 2023

Published in: Russian Journal of Numerical Analysis and Mathematical Modelling (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1910.12686

zbMATH Keywords

function approximationgreedy approximationdeep ReLU networks

Mathematics Subject Classification ID

Algorithms for approximation of functions (65D15) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Related Items (1)

Numerical computation of partial differential equations by hidden-layer concatenated extreme learning machine

Cites Work

• Unnamed Item
• Greedy function approximation: A gradient boosting machine.
• Approximation and estimation bounds for artificial neural networks
• Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem
• Gradient descent optimizes over-parameterized deep ReLU networks
• Error bounds for approximations with deep ReLU networks
• Approximation and learning by greedy algorithms
• Deep ReLU networks and high-order finite element methods
• Error bounds for approximations with deep ReLU neural networks in Ws,p norms
• Orthogonal Matching Pursuit for Sparse Signal Recovery With Noise
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Growing axons: greedy learning of neural networks with application to function approximation