2004-05-14Z 2011-03-11T08:55:36Z http://cogprints.org/id/eprint/3633 This item is in the repository with the URL: http://cogprints.org/id/eprint/3633 2004-05-14Z

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.

Harri Valpola