COMPLEXITY PURSUIT: COMBINING NONGAUSSIANITY AND AUTOCORRELATIONS FOR SIGNAL SEPARATION
Aapo Hyv#rinen, http://www.cis.hut.fi/aapo/
aapo.hyvarinen@hut.fi
A generalization of projection pursuit for time series,
i.e. signals with time structure, is introduced. The goal
is to ønd projections of time series that have interesting
structure. We deøne the interestingness using criteria
related to Kolmogorooe Complexity or coding length:
Interesting signals are those that can be coded with a
short code length. We derive a simple approximation
of coding length that takes into account both the non
gaussianity and the autocorrelations of the time series.
Also, we derive a simple algorithm for its approximative
optimization. The resulting method is closely related to
blind separation of nongaussian, timedependent source
signals.