Leveraging Language into Learning

Book One

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 20

Doctoral Consortium

I hypothesize that learning a vocabulary to communicate between components of a system is equivalent to general learning. Moreover, I assert that some problems of general learning, such as eliminating bad hypotheses, deepening shallow representations, and generation of near-misses, will become simpler when refactored into communication learning problems.