%A Harri Valpola
%T Behaviourally meaningful representations from normalisation and context-guided denoising
%X Many existing independent component analysis algorithms include a preprocessing stage where the inputs are sphered.  This amounts to normalising the data such that all correlations between the variables are removed.  In this work, I show that sphering allows very weak contextual modulation to steer the development of meaningful features. Context-biased competition has been proposed as a model of covert attention and I propose that sphering-like normalisation also allows weaker top-down bias to guide attention.

%D 2004
%I University of Zurich
%L cogprints3633

<script src="//archive-bar.soton.ac.uk/archive-bar.js"></script>