Multilayer feedforward networks with a nonpolynomial activation function can approximate any function
- 1 January 1993
- journal article
- research article
- Published by Elsevier in Neural Networks
- Vol. 6 (6) , 861-867
- https://doi.org/10.1016/s0893-6080(05)80131-5
Abstract
No abstract availableKeywords
This publication has 9 references indexed in Scilit:
- Fundamentality of Ridge FunctionsJournal of Approximation Theory, 1993
- Approximation by ridge functions and neural networks with one hidden layerJournal of Approximation Theory, 1992
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- Approximating and learning unknown mappings using multilayer feedforward networks with bounded weightsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Connectionist learning proceduresArtificial Intelligence, 1989
- On the approximate realization of continuous mappings by neural networksNeural Networks, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- Theorie Generale des Fonctions Moyenne-PeriodiquesAnnals of Mathematics, 1947