dgranata / intrinsic-dimension

Python code for intrinsic dimension estimation of generic datasets

Intrinsic-Dimension

Python code for intrinsic dimension estimation of generic datasets, from the paper:

Daniele Granata, Vincenzo Carnevale "Accurate estimation of intrinsic dimension using graph distances: unraveling the geometric complexity of datasets" Scientific Report, 6, 31377 (2016) https://www.nature.com/articles/srep31377

Please address comments and questions to [email protected]

INSTALLATION:

ID_fit.py use standard python libraries and packages like:

• numpy
• scipy
• scikit-learn (see installation tips at http://scikit-learn.org/stable/install.html)

intrinsic-dimension's Issues

ID_fit.py

line 267-269 in ID_fit.py
if a<0. : rmax = -b/a/2. std=n.sqrt(-1/a/2.) # it was a0
why the std is calculated like this？ what a0 refers to?