Meaningful Models: Utilizing Conceptual Structure to Improve Machine Learning Interpretability

2016/07/01 by Nick Condry, Condry, Nick · 1 voice · 1 citation
Computer Science · Mathematics · #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (stat.ML) #Machine Learning and Data Classification #Topic Modeling #cs.AI #stat.ML

paper · pdf · doi:10.48550/arxiv.1607.00279

5 pages, 3 figures, presented at 2016 ICML Workshop on Human Interpretability in Machine Learning (WHI 2016), New York, NY

arxiv created 2016/07/01 · openalex publication_date 2016/07/01 · arxiv published 2016/07/01 · arxiv updated 2016/07/04 · openalex created_date 2016/07/22 · openalex updated_date 2026/07/28

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.

Cited by

• A Categorisation of Post-hoc Explanations for Predictive Models

Discussions

• Utilizing Conceptual Structure to Improve Machine Learning Interpretability [hn, 1 points, 0 comments]

Related

• Learning Interpretable Concepts: Unifying Causal Representation Learning and Foundation Models
• "I know it when I see it". Visualization and Intuitive Interpretability
• The Need for Interpretable Features: Motivation and Taxonomy
• Techniques for Interpretable Machine Learning
• Definitions, methods, and applications in interpretable machine learning