|
pulsatrix 1.1.0
|
Explainers that use a model's gradients, activations, or internal structure directly. More...

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