On stochastic approximation algorithms for classes of PAC learning problems
Nageswara S. V. Rao, V. R. R. Uppuluri, E.M. Oblow · 2002
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]/sup 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.>