info:oai:cogprints.org:3633info:ofi/fmt:xml:xsd:oai_dc Behaviourally meaningful representations from normalisation and context-guided denoising Valpola, Harri Computational Neuroscience Machine Learning Neural Nets Artificial Intelligence 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. 2004-05 Departmental Technical Report NonPeerReviewed application/pdf http://cogprints.org/3633/1/tr04a.pdf Valpola, Harri (2004) Behaviourally meaningful representations from normalisation and context-guided denoising. [Departmental Technical Report] http://cogprints.org/3633/