Machine learning interpretability and explainability in physics analyzed

This paper reviews the concepts of interpretability and explainability within the context of machine learning applied to physics. It defines interpretability as the structural transparency of a model and explainability as its ability to map onto domain knowledge. The authors discuss the inherent trade-offs, necessary contexts, and available tools for achieving these qualities, emphasizing that machine-learned models are subject to the same scientific scrutiny as traditional models. The paper highlights that interpretability and explainability are deliberate design choices rather than inherent properties, and stresses the importance of task specification and intervention plans in model design. AI

IMPACT Clarifies core concepts for researchers applying machine learning in scientific domains.

RANK_REASON The item is an academic paper discussing concepts related to machine learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Explainability
• Interpretability
• Machine Learning
• Physics

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →