CogprintsBehaviourally meaningful representations from normalisation and context-guided denoisingHarriValpolaauthorMany 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. Computational NeuroscienceMachine LearningNeural NetsArtificial Intelligence2004-05Departmental Technical Report

For work being deposited by its own author: In self-archiving this collection of files and associated bibliographic metadata, I grant Cogprints the right to store them and to make them permanently available publicly for free on-line. I declare that this material is my own intellectual property and I understand that Cogprints does not assume any responsibility if there is any breach of copyright in distributing these files or metadata. (All authors are urged to prominently assert their copyright on the title page of their work.)

For work being deposited by someone other than its author: I hereby declare that the collection of files and associated bibliographic metadata that I am archiving at Cogprints) is in the public domain. If this is not the case, I accept full responsibility for any breach of copyright that distributing these files or metadata may entail.

Clicking on the deposit button indicates your agreement to these terms.