0404319 - UIVT-O 20010102 RIV AT eng C - Conference Paper (international conference)
Kůrková, Věra - Sanguineti, M.
Tight Bounds on Rates of Neural-Network Approximation.
Artificial Neural Networks - ICANN'2001. Berlin: Springer-Verlag, 2001 - (Dorffner, G.; Bischof, H.; Hornik, K.), s. 277-282. Lecture Notes in Computer Science, 2130. ISBN 3-540-42486-5. ISSN 0302-9743.
[ICANN 2001 International Conference on Artificial Neural Networks /11./. Vienna (AT), 21.08.2001-25.08.2001]
R&D Projects: GA ČR GA201/00/1489
Institutional research plan: AV0Z1030915
Keywords : complexity of neural networks * rates of approximation * perceptron networks
Subject RIV: BA - General Mathematics

Complexity of neural networks measured by the number of hidden units is studied in terms of rates of approximation. Limitations of improvements of upper bounds of the order of O(n exp(-1/2)) on such rates are investigated for perceptron networks with some periodic and some sigmoidal activation functions.
Permanent Link: http://hdl.handle.net/11104/0124578