A form of prototypes defined as tuples of marginal probability distribution
s is introduced. Addition and subtraction operations on such prototypes are
then described. A brief introduction to the mass assignment theory of the
probability of fuzzy events is given, and it is shown how fuzzy sets can se
rve as conceptual descriptions of probability distributions. Hence fuzzy de
scriptions of prototypes can be derived and these can be used for inference
as well as enabling rule based representations of a set of prototypes to b
e formed. A prototype induction algorithm, based on these ideas together wi
th the addition and subtraction operations, is described. The potential of
this approach is then illustrated by its application to a number of model a
nd rear world machine learning problems. (C) 1999 John Wiley & Sons, Inc.