Toward a Unified Theory of Understanding: A Conceptual Analysis for Natural and Artificial Understanding
TL;DR
Two primary methods for assessing artificial understanding are discussed: behavioral methods measuring generalizability and mechanistic analyses revealing causal mechanisms of the neural network, which discuss the limitations of these methods.
Abstract
Understanding is the foundational component of intelligence that makes adaptation to novel states possible. As artificial intelligence models advance toward artificial general and superintelligence, an objective, in contrast to human-centered, theory of understanding is required. One merit of an objective conceptual analysis of understanding is that it would unify human and artificial understanding. This study defines understanding as well-integrated use of reasoning across a network of conceptual, logical, and causal relationships, which are situated on an efficient conceptual web. A central evolutionary function of understanding is the capacity to generalize knowledge into novel situations. This renders machine learning’s concept of “generalization” a measure of understanding. The paper discusses two primary methods for assessing artificial understanding: behavioral methods measuring generalizability and mechanistic analyses revealing causal mechanisms of the neural network. We discuss the limitations of these methods. The most important problem, as this paper defends, is the difficulty of measuring objective understanding in contrast to human understanding.