Loading Deep Networks Is Hard: The Pyramidal Case

DOI10.1162/0899766053011519zbMath1093.68091OpenAlexW2132557391MaRDI QIDQ5696500

David Windisch

Publication date: 18 October 2005

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/0899766053011519

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17)

Cites Work

• Hardness results for neural network approximation problems
• Robust trainability of single neurons
• Theory of majority decision elements
• Training a Single Sigmoidal Neuron Is Hard
• Learning representations by back-propagating errors