http://cogprints.org/3633/ Behaviourally meaningful representations from normalisation and context-guided denoising 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. Valpola, Harri Computational Neuroscience Machine Learning Neural Nets Artificial Intelligence Harri Valpola