Computational limitations on training sigmoid neural networks

DOI10.1016/0020-0190(93)90064-GzbMath0780.68101MaRDI QIDQ685499

Klaus-Uwe Höffgen

Publication date: 6 February 1994

Published in: Information Processing Letters (Search for Journal in Brave)

zbMATH Keywords

neural networkstraining vectors

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

Training a Single Sigmoidal Neuron Is Hard

Cites Work

• Robust trainability of single neurons
• Unnamed Item

This page was built for publication: Computational limitations on training sigmoid neural networks