\magnification=1200
\baselineskip=20pt
\nopagenumbers
\font\big=cmr12 scaled \magstep2

\centerline{\bf STANFORD UNIVERSITY}
\centerline{\bf DEPARTMENT OF STATISTICS}
\centerline{\big DEPARTMENT SEMINAR}
\bigskip

\baselineskip=12pt
\centerline{4:15 p.m., Wednesday, July 10, 2002}
\centerline{Sequoia Hall Room 200}
\centerline{(Cookies at 3:45 in 1st Floor Lounge)}

\bigskip
\baselineskip=15pt
\centerline{\sl Aapo Hyvarinen}
\centerline{\sl Helsinki University of Technology}
\bigskip
\centerline{\bf Independent Components Analysis: sparsity and  extensions}
\bigskip

The talk will be an expository talk on ICA based on the following papers.

\noindent A. Hyvärinen, P.O. Hoyer and M. Inki. ``Topographic Independent
Component Analysis.'' Neural Computation, 13(7):1525-1558, 2001.

This paper introduces an extension of ICA. The dependencies of the estimated
"independent" components are visualized as a topographic order. A new
principle for topographic organization, based on higher-order
statistics. Applied on image data, both topography and complex cell
properties emerge.

\noindent A. Hyvärinen and P.O. Hoyer. ``Emergence of phase and shift invariant
features by decomposition of natural images into independent feature
subspaces.''  Neural Computation, 12(7):1705-1720, 2000.

This paper presents a simpler extension of ordinary ICA which was a precursor of
topographic ICA. Here the goal of independence of scalar independent
components is replaced by the independence of the norms of
projections on certain subspaces. This is applied on image data, and
complex cell properties are shown to emerge.

\bye