Stochastic choice of basis functions in adaptive function approximation and the functional-link net
- 1 January 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 6 (6) , 1320-1329
- https://doi.org/10.1109/72.471375
Abstract
A theoretical justification for the random vector version of the functional-link (RVFL) net is presented in this paper, based on a general approach to adaptive function approximation. The approach consists of formulating a limit-integral representation of the function to be approximated and subsequently evaluating that integral with the Monte-Carlo method. Two main results are: (1) the RVFL is a universal approximator for continuous functions on bounded finite dimensional sets, and (2) the RVFL is an efficient universal approximator with the rate of approximation error convergence to zero of order O(C/ radicaln), where n is number of basis functions and with C independent of n. Similar results are also obtained for neural nets with hidden nodes implemented as products of univariate functions or radial basis functions. Some possible ways of enhancing the accuracy of multivariate function approximations are discussed.Keywords
This publication has 19 references indexed in Scilit:
- Approximation and estimation bounds for artificial neural networksMachine Learning, 1994
- Universal approximation bounds for superpositions of a sigmoidal functionIEEE Transactions on Information Theory, 1993
- Multilayer feedforward networks with a nonpolynomial activation function can approximate any functionNeural Networks, 1993
- Some new results on neural network approximationNeural Networks, 1993
- Decision theoretic generalizations of the PAC model for neural net and other learning applicationsInformation and Computation, 1992
- A Simple Lemma on Greedy Approximation in Hilbert Space and Convergence Rates for Projection Pursuit Regression and Neural Network TrainingThe Annals of Statistics, 1992
- Minimum complexity density estimationIEEE Transactions on Information Theory, 1991
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989