Caleb Geniesse's repositories
landmark_cover
A landmark-based cover for KeplerMapper
reciprocal_isomap
A reciprocal variant of Isomap for robust non-linear dimensionality reduction in Python
3d-force-graph
3D force-directed graph component using ThreeJS/WebGL
characterizing-pinns-failure-modes
Characterizing possible failure modes in physics-informed neural networks.
Decorated-Merge-Trees
Tools for generating and comparing Decorated Merge Trees, enriched persistence-based topological data descriptors.
dnn-mode-connectivity
Mode Connectivity and Fast Geometric Ensembles in PyTorch
giotto-deep
Deep learning made topological.
kepler-mapper
Kepler Mapper: A flexible Python implementation of the Mapper algorithm.
kepler-mapper-backend-example
Demonstration of how to use Kepler Mapper as backend.
loss_landscape_taxonomy
[NeurIPS 2021] code for "Taxonomizing local versus global structure in neural network loss landscapes" https://arxiv.org/abs/2107.11228
mapper_comparison
Code for paper Mapper Comparison with Wasserstein Metrics
ohbm2020-posters
Centralized registry of Jitsi rooms for OHBM 2020 posters.
pytorch_cluster
PyTorch Extension Library of Optimized Graph Cluster Algorithms
pytorch_geometric
Geometric Deep Learning Extension Library for PyTorch
sparse_attention
Examples of using sparse attention, as in "Generating Long Sequences with Sparse Transformers"
TopologyLayer
A Topology Layer for Machine Learning : Persistent Homology + Features for PyTorch
understanding-umap
Understanding the theory behind UMAP
WeightWatcher
The WeightWatcher tool for predicting the accuracy of Deep Neural Networks