Understanding the Meaning of Understanding

TL;DR

This paper explores the challenge of determining whether a machine truly understands an abstract concept without direct testing, focusing on the metaphysical implications and proposing a conceptual framework.

Contribution

It introduces a novel approach to assess machine understanding of concepts indirectly, emphasizing the importance of equivalence classes and metaphysical considerations.

Findings

Proposes a framework for understanding machine comprehension without direct questions

Highlights metaphysical issues in defining understanding

Suggests equivalence classes as a means to isolate meaning

Abstract

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.