|
pulsatrix 1.1.0
|
Persistent homology of a layer's representations, as a typed pipeline: a point cloud built from activations, its distances, the filtration, persistence diagrams and their vectorizations. More...
Files | |
| file | diagram_distance.hpp |
| Distances between persistence diagrams, bottleneck and Wasserstein, and Certified<T>, a value with the error bounds behind it. | |
| file | distance_matrix.hpp |
| Pairwise Euclidean distances of a point cloud, computed with one GEMM on any backend, with a certified bound on their floating-point error. | |
| file | h0.hpp |
| H0 persistence, the clusters of a point cloud across scales, from its minimum spanning tree. | |
| file | landmarks.hpp |
| Farthest-point landmarks: a subset of a large point cloud that covers it, with a certified bound on what persistent homology loses by using the subset. | |
| file | persistence_diagram.hpp |
| A persistence diagram: the features of one homology dimension, each born at one scale and dying at a larger one. | |
| file | point_cloud.hpp |
| The input to topological data analysis: a layer's activations as a set of points, one row per input or per position, gathered across batches. | |
| file | rips_persistence.hpp |
| Persistent homology of the Vietoris-Rips filtration in every dimension up to a maximum: components (H0), loops (H1), voids (H2) and beyond, with each feature's critical edges and a representative cocycle. | |
| file | rtd.hpp |
| Representation Topology Divergence (RTD): how differently two representations of the same inputs are shaped, cluster by cluster and loop by loop, and CompareRepresentations(), one report with CKA, mutual-kNN alignment and RTD side by side. | |
| file | significance.hpp |
| Is a loop real? Significance tests for persistence diagrams: the universal null distribution, bootstrap confidence bands, and baseline comparisons against Gaussian clouds or a random network. | |
| file | vectorization.hpp |
| Turning a persistence diagram into numbers for probes, statistics and plots: Betti curves, persistence landscapes, persistence images and persistent entropy. | |
Persistent homology of a layer's representations, as a typed pipeline: a point cloud built from activations, its distances, the filtration, persistence diagrams and their vectorizations.