On the approximation by neural networks with bounded number of neurons in hidden layers
- 1 September 2014
- journal article
- Published by Elsevier BV in Journal of Mathematical Analysis and Applications
- Vol. 417 (2), 963-969
- https://doi.org/10.1016/j.jmaa.2014.03.092
Abstract
No abstract availableFunding Information
- SOCAR Science Foundation of Azerbaijan (SOCAR EF 2013)
This publication has 23 references indexed in Scilit:
- Approximation by neural networks with weights varying on a finite set of directionsJournal of Mathematical Analysis and Applications, 2012
- On the representation by linear superpositionsJournal of Approximation Theory, 2008
- The estimate for approximation error of neural networks: A constructive approachNeurocomputing, 2008
- Approximation and estimation bounds for artificial neural networksMachine Learning, 1994
- Approximations of continuous functionals by neural networks with application to dynamic systemsIEEE Transactions on Neural Networks, 1993
- Approximation of continuous functions on Rd by linear combinations of shifted rotations of a sigmoid function with and without scalingNeural Networks, 1992
- Approximation by ridge functions and neural networks with one hidden layerJournal of Approximation Theory, 1992
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- Representation Properties of Networks: Kolmogorov's Theorem Is IrrelevantNeural Computation, 1989
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989