History dependent stochastic automata: A formal view of evolutionary learning
Stefan Waner, Harold M. Hastings · International Journal of Intelligent Systems · 1988
We develop a theoretical framework for the study of evolutionary learning systems. the formalism we use is that of history dependent stochastic automata with suitable structure, as well as related structures. This formalism provides a natural setting in which to describe the learning of classification hierarchies, of control hierarchies and notions of selfreference, all of which are derived as consequences of the ability to learn by association.