This site has been permanently archived. This is a static copy provided by the University of Southampton.
--- abstract: "We apply Slow Feature Analysis (SFA) to image sequences generated from natural images using a range of spatial transformations. An analysis of the resulting receptive fields shows that they have a rich spectrum of invariances and share many properties with complex and hypercomplex cells of the primary visual cortex. Furthermore, the dependence of the solutions on the statistics of the transformations is investigated.\n" altloc: [] chapter: ~ commentary: ~ commref: ~ confdates: August 2002 conference: International Conference on Artificial Neural Networks 2002 confloc: 'Madrid, Spain' contact_email: ~ creators_id: [] creators_name: - family: Berkes given: Pietro honourific: '' lineage: '' - family: Wiskott given: Laurenz honourific: '' lineage: '' date: 2002 date_type: published datestamp: 2003-01-09 department: ~ dir: disk0/00/00/27/06 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: - family: Dorronsoro given: Jos� R. honourific: '' lineage: '' eprint_status: archive eprintid: 2706 fileinfo: /style/images/fileicons/application_postscript.png;/2706/1/I0220.ps full_text_status: public importid: ~ institution: ~ isbn: ~ ispublished: pub issn: ~ item_issues_comment: [] item_issues_count: 0 item_issues_description: [] item_issues_id: [] item_issues_reported_by: [] item_issues_resolved_by: [] item_issues_status: [] item_issues_timestamp: [] item_issues_type: [] keywords: 'Complex cells, slow feature analysis, temporal slowness, model , spatio-temporal, receptive fields' lastmod: 2011-03-11 08:55:08 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: 81-86 pubdom: FALSE publication: ~ publisher: Springer Verlag refereed: TRUE referencetext: ~ relation_type: [] relation_uri: [] reportno: ~ rev_number: 10 series: ~ source: ~ status_changed: 2007-09-12 16:46:23 subjects: - neuro-mod - comp-neuro-sci - comp-sci-mach-vis - bio-theory succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: Applying Slow Feature Analysis to Image Sequences Yields a Rich Repertoire of Complex Cell Properties type: confpaper userid: 3740 volume: ~