Interpreting "Interpretability" and Explaining "Explainability" in Machine Learning in Physics
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Model Explanations under Calibration
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 SystemsvalidLatentExplainer: Explaining Latent Representations in Deep Generative Models with Multimodal Large Language Models
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 QuantificationDomain Knowledge Aided Explainable Artificial Intelligence for Intrusion Detection and Response
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 DetectionInterpretML: A Unified Framework for Machine Learning Interpretability
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 LearningTowards Explainability of Machine Learning Models in Insurance Pricing
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