?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Behaviourally+meaningful+representations+from+normalisation+and+context-guided+denoising&rft.creator=Valpola%2C+Harri&rft.subject=Computational+Neuroscience&rft.subject=Machine+Learning&rft.subject=Neural+Nets&rft.subject=Artificial+Intelligence&rft.description=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%2C+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.%0A&rft.date=2004-05&rft.type=Departmental+Technical+Report&rft.type=NonPeerReviewed&rft.format=application%2Fpdf&rft.identifier=http%3A%2F%2Fcogprints.org%2F3633%2F1%2Ftr04a.pdf&rft.identifier=++Valpola%2C+Harri++(2004)+Behaviourally+meaningful+representations+from+normalisation+and+context-guided+denoising.++%5BDepartmental+Technical+Report%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F3633%2F