Interpretability in SciML requires mechanistic understanding rather than sparsity, and prior knowledge is often essential for interpretable scientific discovery.
Title resolution pending
3 Pith papers cite this work, alongside 139 external citations. Polarity classification is still indexing.
3
Pith papers citing it
139
external citations · OpenAlex
representative citing papers
Gradient- and perturbation-based XAI methods show substantial agreement on frontal, temporal, and posterior EEG regions for an InceptionTime MDD classifier, while DeepSHAP differs, with overall partial convergence and method-dependent variability.
The paper defines interpretability as model structural transparency and explainability as scientific content mapping, discusses their trade-offs, and frames both as deliberate modeling choices for ML in physics.
citing papers explorer
-
On the definition and importance of interpretability in scientific machine learning
Interpretability in SciML requires mechanistic understanding rather than sparsity, and prior knowledge is often essential for interpretable scientific discovery.
-
Comparing Post-Hoc Explainable AI Methods for Interpreting Black-Box EEG Models in Depression Detection
Gradient- and perturbation-based XAI methods show substantial agreement on frontal, temporal, and posterior EEG regions for an InceptionTime MDD classifier, while DeepSHAP differs, with overall partial convergence and method-dependent variability.
-
Interpreting "Interpretability" and Explaining "Explainability" in Machine Learning in Physics
The paper defines interpretability as model structural transparency and explainability as scientific content mapping, discusses their trade-offs, and frames both as deliberate modeling choices for ML in physics.