Title :
On stochastic approximation algorithms for classes of PAC learning problems
Author :
Rao, Nageswara S V ; Uppuluri, V.R.R. ; Oblow, E.M.
Author_Institution :
Center for Eng. Syst. Adv. Res., Oak Ridge Nat. Lab., TN, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
The classical stochastic approximation methods are shown to yield algorithms to solve several formulations of the PAC learning problem defined on the domain [0, 1]d. Under some assumptions on differentiability of the probability measure functions, simple algorithms to solve some PAC learning problems are proposed based on networks of nonpolynomial units (e.g. artificial neural networks). Conditions on the sizes of the samples required to ensure the error bounds are derived using martingale inequalities
Keywords :
approximation theory; learning (artificial intelligence); neural nets; PAC learning problems; error bounds; martingale inequalities; neural networks; nonpolynomial unit networks; probability measure functions; probably approximately correct learning; stochastic approximation algorithms; Approximation algorithms; Approximation methods; Artificial neural networks; Convergence; Error correction; Laboratories; Neural networks; Stochastic processes; Systems engineering and theory; US Government;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374279
