On the infeasibility of training neural networks with small mean-squared error

DOI10.1109/18.737520zbMath0981.68138OpenAlexW2071611037MaRDI QIDQ4701218

Van H. Vu

Publication date: 21 November 1999

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

Full work available at URL: https://semanticscholar.org/paper/eaafe898c9bf6b7e79ffa94d5ca21b2d55b4d532

zbMATH Keywords

NP-completenesstraining neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items

Ridgelets: estimating with ridge functions, Theory of Classification: a Survey of Some Recent Advances, Local greedy approximation for nonlinear regression and neural network training.