Recursion theoretic models of learning: Some results and intuitions

Abstract

Very general models of learning were introduced and compared. Each of the models reflected certain situations that occur in common observations of human learning. For example, teams of learners can learn more than any individual. It was shown that sometimes to learn one concept, another must be mastered first. Sometimes, it is necessary to learn several functions simultaneously in order to learn any of them. An advantage in asking questions about the phenomenon under investigation, as opposed to waiting for data to arrive, is that it enhances learning potential. The more powerful the questions that can be formulated, the more that can be learned. Finally, it was shown that there is an advantage in some forms of procrastination in learning.

DOI: 10.1007/BF01534453

Cite this paper

@article{Smith1995RecursionTM, title={Recursion theoretic models of learning: Some results and intuitions}, author={Carl H. Smith and William I. Gasarch}, journal={Annals of Mathematics and Artificial Intelligence}, year={1995}, volume={15}, pages={151-166} }