Meaningful Models: Utilizing Conceptual Structure to Improve Machine Learning Interpretability
This addresses the need for interpretable models in daily life applications, though it appears incremental as it builds on existing cognitive insights.
The paper tackles the problem of machine learning model interpretability by leveraging conceptual structure from human cognition, proposing a novel classification of concepts into 'form' and 'function' to enhance understandability, with the result being improved interpretability that bridges domain experts and non-expert users.
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.