Modelling Productivity with the Gradual Learning Algorithm: The Problem of Accidentally Exceptionless Generalizations

Abstract

This chapter develops a model that can handle all configurations of gradience and categoricalness. It believes that the solution lies in the trade-off between reliability and generality. It shows how the previous approach to the problem was not enough, and suggests a novel approach using the gradual learning algorithm (GLA), adapted to more general limitations. Keywords: gradual learning algorithm; gradience; generality; prototype; categoricalness; optimality theory; generalizations