Skip to content

Releases: mmp2/megaman

Version 0.3

04 Nov 22:25
Compare
Choose a tag to compare

Fixing Python 3.5 bug with cyflann.

New num_checks parameter for cyflann, kdtrees.

v0.1.1 bug fix

10 Mar 00:57
Compare
Choose a tag to compare
  • changes to setup.py to be compatible with conda packaging

megaman v0.1: manifold learning for millions of points

10 Mar 00:59
Compare
Choose a tag to compare

Initial release of megaman, containing scalable algorithms for manifold learning including:

  • Locally Linear Embedding
  • Local Tangent Space Alignment
  • Isomap
  • Spectral Embedding

These algorithms use FLANN, PYAMG, LOBPCG, ARPACK, and other fast libraries to power through the computational hurdles of manifold learning algorithms.