L. Bochereau et al., A GENERAL FRAMEWORK FOR SUPERVISED LEARNING - PROBABLY ALMOST BAYESIAN ALGORITHMS, Journal of economic dynamics & control, 18(1), 1994, pp. 97-118
The paper proposes the concept of Probably Almost Bayesian (PAB) algor
ithms generalizing a definition given by Valiant in his theory of the
learnable. PAB algorithms are defined as algorithms that probably appr
oximate the Bayesian optimum when the training set size tends to infin
ity, in polynomial time with respect to the training set size. We pres
ent this concept in the framework of the decision theory and we suppor
t this definition by giving examples of such algorithms, particularly
in the field of artificial neural networks.