A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2010; you can also visit the original URL.
The file type is application/pdf
.
Entropic graphs for manifold learning
The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003
A b m m -We propose a new algorithm that simultaneously eslimates the intrinsic dimension and intrinsic entropy 01 random data sets lying on smooth manifolds. The method is based on asymptotic properties 01 entropic graph constructions. In particular, n e compute the Euclidean k-nearest neighbors (k-NN) graph oyer the sample points and use its overall total edge length to estimate intrinsic dimension and entropy. The algorithm is \,alidated on standard synthetic manifolds. 0-7803-8104-1/03/$17.00 02003 IEEE
doi:10.1109/acssc.2003.1291928
fatcat:mxwiex7vcjhjpnqy7p675epkca