--- abstract: "A central mystery of visual perception is the classical problem of invariant object recognition: Different appearances of an object can be perceived as ``the same'', despite, e.g., changes in position or illumination, distortions, or partial occlusion by other objects. This article reports on a recent email discussion over the question whether a neural network can learn the simplest of these invariances, i.e. generalize over the position of a pattern on the input layer, including the author's view on what ``learning shift-invariance'' could mean. That definition leaves the problem unsolved. A similar problem is the one of learning to detect symmetries present in an input pattern. It has been solved by a standard neural network requiring some 70000 input examples. Both leave some doubt if backpropagation learning is a realistic model for perceptual processes. Abandoning the view that a stimulus-response system showing the desired behavior must be learned from scratch, yields a radically different solution. Perception can be seen as an active process that rapidly converges from some initial state to an ordered state, which in itself codes for a percept. As an example, I will present a solution to the visual correspondence problem, which greatly alleviates both problems mentioned above." altloc: [] chapter: ~ commentary: ~ commref: ~ confdates: ~ conference: ~ confloc: ~ contact_email: ~ creators_id: [] creators_name: - family: Würtz given: Rolf P. honourific: '' lineage: '' date: 1998 date_type: published datestamp: 1998-08-05 department: ~ dir: disk0/00/00/05/07 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: [] eprint_status: archive eprintid: 507 fileinfo: /style/images/fileicons/application_postscript.png;/507/2/rolf%2Dcogsys98.ps full_text_status: public importid: ~ institution: ~ isbn: ~ ispublished: ~ 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: ~ lastmod: 2011-03-11 08:54:00 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: ~ pubdom: FALSE publication: ~ publisher: ~ refereed: TRUE referencetext: ~ relation_type: [] relation_uri: [] reportno: ~ rev_number: 10 series: ~ source: ~ status_changed: 2007-09-12 16:29:24 subjects: - bio-ani-cog - cog-psy - comp-sci-complex-theory - comp-sci-mach-vis - comp-sci-neural-nets - neuro-mod succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: 'Neural networks as a model for visual perception: what is lacking?' type: preprint userid: 445 volume: ~