Sciweavers

56
Voted
NIPS
2001

Scaling Laws and Local Minima in Hebbian ICA

14 years 10 months ago
Scaling Laws and Local Minima in Hebbian ICA
We study the dynamics of a Hebbian ICA algorithm extracting a single non-Gaussian component from a high-dimensional Gaussian background. For both on-line and batch learning we find that a surprisingly large number of examples are required to avoid trapping in a sub-optimal state close to the initial conditions. To extract a skewed signal at least
Magnus Rattray, Gleb Basalyga
Added 31 Oct 2010
Updated 31 Oct 2010
Type Conference
Year 2001
Where NIPS
Authors Magnus Rattray, Gleb Basalyga
Comments (0)