Parallelism Increases Iterative Learning Power

Abstract

Iterative learning ($\textbf{It}$-learning) is a Gold-style learning model in which each of a learner’s output conjectures may depend only upon the learner’s current conjecture and the current input element. Two extensions of the $\textbf{It}$-learning model are considered, each of which involves parallelism. The first is to run, in parallel, distinct instantiations of a single learner on each input element. The second is to run, in parallel, n individual learners incorporating the first extension, and to allow the n learners to communicate their results. In most contexts, parallelism is only a means of improving efficiency. However, as shown herein, learners incorporating the first extension are more powerful than $\textbf{It}$-learners, and, collective learners resulting from the second extension increase in learning power as n increases. Attention is paid to how one would actually implement a learner incorporating each extension. Parallelism is the underlying mechanism employed.