scientific article; zbMATH DE number 2080651

zbMATH Open1050.68116MaRDI QIDQ4473545FDOQ4473545

Authors: Jiří Šíma 

Publication date: 4 August 2004

Full work available at URL: http://link.springer.de/link/service/series/0558/bibs/2225/22250092.htm

Title of this publication is not available (Why is that?)

Recommendations

• Training a Single Sigmoidal Neuron Is Hard
• The computational intractability of training sigmoidal neural networks
• Hardness results for neural network approximation problems
• Complexity of training ReLU neural network
• On the infeasibility of training neural networks with small mean-squared error

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17)

Cited In (4)

• Title not available (Why is that?)
• Computational limitations on training sigmoid neural networks
• Training a Single Sigmoidal Neuron Is Hard
• Hardness results for neural network approximation problems

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4473545)