Cognitive Thermometers: Machine Learning and Logical Complexity

2026-10-07

AI Summary

This study addresses the limitation that traditional measures of semantic complexity are highly sensitive to specific logical languages, lacking an objective and unified metric. To overcome this, this work proposes employing machine learning as a "cognitive thermometer" to evaluate semantic complexity, integrating logical complexity analysis with semantic typology to construct a unified framework bridging symbolic logic and connectionist AI. The primary contribution lies in establishing a new paradigm demonstrating that machine learning outperforms purely logic-based complexity metrics in explaining semantic typology. Empirical findings confirm that these two approaches frequently converge; however, where they diverge, machine learning offers superior explanatory power. This effectively transcends the constraints of traditional logical definitions, achieving a theoretical unification in the measurement of semantic complexity.

Abstract

How does the human mind represent semantic categories? Why do natural languages favor certain meanings over others? Prior explanations have relied on logical definability and complexity, but these are highly sensitive to the choice of logical language, rendering some design choices unmotivated. In this article, we propose that machine learning provides a somewhat more agnostic approach to measuring semantic complexity. We review emerging evidence that logic and machine learning often yield converging results on relative complexity and its resulting effects in semantic typology. Where they diverge, learning appears to be a better explanation than logical complexity. We argue that treating machine learning models as ``cognitive thermometers'' enables a unified approach to complexity that bridges symbolic logic and connectionist AI.

Problem

• semantic complexity
• cognitive representation
• semantic typology
• machine learning
• logical definability

Innovation

• Machine Learning
• Semantic Complexity
• Cognitive Thermometers
• Logical Definability
• Connectionist AI