paper-with-me

Papers

Interpreting "Interpretability" and Explaining "Explainability" in Machine Learning in Physics

2026-06-24 · Rikab Gambhir, Luisa Lucie-Smith, Jesse Thaler arxiv

We review the concepts of interpretability and explainability as they apply to machine learning in physics. We define interpretability as concerning the structural transparency of a model (the ability to understand or approximate its inner workings) and explainability as concerning the scientific content of a model (the ability to map it onto domain knowledge). We discuss the trade-offs each entails (interpretability vs. expressivity; explainability vs. adaptability), the contexts in which each is needed, and the intrinsic and post-hoc tools available for achieving them. Throughout, we emphasize that machine-learned models are subject to the same scientific questions as classical models, differing only in scale, and that interpretability and explainability are best understood as deliberate modeling choices rather than inherent properties. We also emphasize the importance of task specification and intervention plans as a core aspect of model design.

📄 PDF Abstract BibTeX arXiv:2606.26228

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Model Explanations under Calibration

2019-06-18 · Rishabh Jain, Pranava Madhyastha

Explaining and interpreting the decisions of recommender systems are becoming extremely relevant both, for improving predictive performance, and providing valid explanations to users. While most of the recent interest ha…

modelRecommendation Systemsvalid

LatentExplainer: Explaining Latent Representations in Deep Generative Models with Multimodal Large Language Models

2024-06-21 · Mengdan Zhu, Raasikh Kanjiani, Jiahui Lu, Andrew Choi 외

Deep generative models like VAEs and diffusion models have advanced various generation tasks by leveraging latent variables to learn data distributions and generate high-quality samples. Despite the field of explainable …

Uncertainty Quantification

Domain Knowledge Aided Explainable Artificial Intelligence for Intrusion Detection and Response

2019-11-22 · Sheikh Rabiul Islam, William Eberle, Sheikh K. Ghafoor, Ambareen Siraj 외

Artificial Intelligence (AI) has become an integral part of modern-day security solutions for its ability to learn very complex functions and handling "Big Data". However, the lack of explainability and interpretability …

Explainable artificial intelligenceIntrusion DetectionNetwork Intrusion Detection

InterpretML: A Unified Framework for Machine Learning Interpretability

2019-09-19 · Harsha Nori, Samuel Jenkins, Paul Koch, Rich Caruana

InterpretML is an open-source Python package which exposes machine learning interpretability algorithms to practitioners and researchers. InterpretML exposes two types of interpretability - glassbox models, which are mac…

Additive modelsBIG-bench Machine Learning

Towards Explainability of Machine Learning Models in Insurance Pricing

2020-03-24 · Kevin Kuo, Daniel Lupton

Machine learning methods have garnered increasing interest among actuaries in recent years. However, their adoption by practitioners has been limited, partly due to the lack of transparency of these methods, as compared …

BIG-bench Machine Learning