Interpretability

Post-hoc explanation methods applied to an already-trained model: whole-model LRP over the rules built into each layer in Deep Learning Modules and Layers, plus model-agnostic and gradient-based explainers. More...

Collaboration diagram for Interpretability:

Modules
	Model-Agnostic Explainers
	Explainers that only need a model's input/output behavior (perturb-and-observe), with no access to gradients or internal activations.
	Gradient-Based Explainers
	Explainers that use a model's gradients, activations, or internal structure directly.
	Layer-wise Relevance Propagation
	Whole-model LRP (LRP, LRPTarget, LRPSeed), rule selection (LRPRule, LRPRuleConfig), Zennit-style composites (lrp_composite) and conservation checks.

Detailed Description

Post-hoc explanation methods applied to an already-trained model: whole-model LRP over the rules built into each layer in Deep Learning Modules and Layers, plus model-agnostic and gradient-based explainers.