The computational intractability of training sigmoidal neural networks

DOI10.1109/18.567673MaRDI QIDQ4336293zbMATHOpenAlexFDO

Authors Lee Kenneth Jones

Publication date 10 November 1997

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/18.567673

zbMATH Keywords

neural networkNP-completenessLipschitzian sigmoidal internal activation functions

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Circuits, networks (94C99)

Recommendations

• Training a Single Sigmoidal Neuron Is Hard
• On the infeasibility of training neural networks with small mean-squared error
• Computational limitations on training sigmoid neural networks
• scientific article; zbMATH DE number 2080651

Cited in

(21)

• scientific article; zbMATH DE number 774006 (Why is no real title available?)
• scientific article; zbMATH DE number 1869613 (Why is no real title available?)
• A mathematical solution to a network construction problem.
• Ill-Conditioning in Neural Network Training Problems
• Some problems in the theory of ridge functions
• Hardness results for neural network approximation problems
• Algorithmic Learning Theory
• Ridgelets: estimating with ridge functions
• Convergence of a least-squares Monte Carlo algorithm for American option pricing with dependent sample data
• scientific article; zbMATH DE number 2080651 (Why is no real title available?)
• Complexity of network training for classes of Neural Networks
• Computational limitations on training sigmoid neural networks
• An unfeasibility view of neural network learning
• On the complexity of loading shallow neural networks
• Loading Deep Networks Is Hard: The Pyramidal Case
• scientific article; zbMATH DE number 67614 (Why is no real title available?)
• On approximate learning by multi-layered feedforward circuits
• Local greedy approximation for nonlinear regression and neural network training.
• scientific article; zbMATH DE number 4155875 (Why is no real title available?)
• Complexity of training ReLU neural network
• Training a Single Sigmoidal Neuron Is Hard

This page was built for publication: The computational intractability of training sigmoidal neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4336293)