Understanding the Meaning of Understanding
This addresses a foundational problem in AI and philosophy regarding machine understanding, but it is incremental as it focuses on theoretical discussion without empirical validation.
The paper tackles the problem of training a machine to detect if another machine has understood a concept without using direct questions, aiming to isolate the absolute meaning of abstract ideas through equivalence classes. It discusses metaphysical implications to provide a plausible reference framework, but does not present concrete results or numbers.
Can we train a machine to detect if another machine has understood a concept? In principle, this is possible by conducting tests on the subject of that concept. However we want this procedure to be done by avoiding direct questions. In other words, we would like to isolate the absolute meaning of an abstract idea by putting it into a class of equivalence, hence without adopting straight definitions or showing how this idea "works" in practice. We discuss the metaphysical implications hidden in the above question, with the aim of providing a plausible reference framework.