Meaningful Models: Utilizing Conceptual Structure to Improve Machine Learning Interpretability

TL;DR

This paper introduces a novel approach to enhance machine learning interpretability by leveraging the conceptual structure of human meaning, classifying concepts by 'form' and 'function' to improve understanding.

Contribution

It proposes a new method of classifying concepts to elucidate meaning and improve model interpretability, bridging the gap between experts and non-experts.

Findings

Concept classification improves interpretability

Enhanced understanding of model decisions

Framework for integrating human conceptual structures

Abstract

The last decade has seen huge progress in the development of advanced machine learning models; however, those models are powerless unless human users can interpret them. Here we show how the mind's construction of concepts and meaning can be used to create more interpretable machine learning models. By proposing a novel method of classifying concepts, in terms of 'form' and 'function', we elucidate the nature of meaning and offer proposals to improve model understandability. As machine learning begins to permeate daily life, interpretable models may serve as a bridge between domain-expert authors and non-expert users.