An unfeasibility view of neural network learning

DOI10.1016/j.jco.2022.101710OpenAlexW4302009122WikidataQ114950931 ScholiaQ114950931MaRDI QIDQ2685066

Joos Heintz, Hvara Ocar, Enrique Carlos Segura, Andrés Rojas Paredes, Luis Miguel Pardo

Publication date: 17 February 2023

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2201.00945

zbMATH Keywords

machine learningactivation functioncontinuously differentiable functionmultilayer neural networkcomplexity lower boundepicycle

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Quiz games as a model for information hiding
• On the computational complexity and geometry of the first-order theory of the reals. I: Introduction. Preliminaries. The geometry of semi-algebraic sets. The decision problem for the existential theory of the reals
• Multilayer feedforward networks are universal approximators
• Sur la complexité du principe de Tarski-Seidenberg
• Neural Network Learning
• Complexity of cylindrical decompositions of sub-Pfaffian

This page was built for publication: An unfeasibility view of neural network learning