pulsatrix 1.1.0
Loading...
Searching...
No Matches
Gradient-Based Explainers

Explainers that use a model's gradients, activations, or internal structure directly. More...

Collaboration diagram for Gradient-Based Explainers:

Files

file  attribution.hpp
 First-class explanation result type – values, method, and metadata together.
 
file  contrastive.hpp
 The contrastive explanation method (CEM; Dhurandhar et al., "Explanations based on the Missing", NeurIPS 2018): pertinent negatives, what is absent from an input and would change its class if present, and pertinent positives, the least of the input that keeps its class on its own (XAI-4).
 
file  counterfactual.hpp
 Counterfactual explanations: gradient-based (Wachter et al. 2017, CFS-5) and model-agnostic (growing spheres, Laugel et al. 2018, CFS-6), and diverse sets with a plausibility score (DiCE, Mothilal et al. 2020, CFS-7).
 
file  explainer_context.hpp
 Stable interface every explainer gets, regardless of type (charter Part 2 SS2).
 
file  explainer_stability.hpp
 Production API for an explainer's repeated-run stability audit metric (charter Phase 4).
 
file  grad_cam.hpp
 Grad-CAM – gradient-weighted class activation mapping over the last conv layer (charter Part 1, Phase 2; theory: xai_context.aDNA's vision_gradcam.md).
 
file  integrated_gradients.hpp
 Integrated Gradients – baseline-interpolated gradient integral (charter Part 1, Phase 2; theory: xai_context.aDNA's vision_integrated_gradients.md).
 
file  saliency.hpp
 Saliency maps – raw gradient of a target output w.r.t. the input (charter Part 1, Phase 2).
 

Detailed Description

Explainers that use a model's gradients, activations, or internal structure directly.