This site has been permanently archived. This is a static copy provided by the University of Southampton.
--- abstract: "This paper presents the double loop feedback model, which is used for structure and data flow modelling through reinforcement learning in an artificial neural network. We first consider physiological arguments suggesting that loops and double loops are widely spread in the exchange flows of the central nervous system. We then demonstrate that the double loop pattern, named a mental object, works as a functional memory unit and we describe the main properties of a double loop resonator built with the classical Hebb's law learning principle in a feedforward basis. In this model, we show how some mental objects aggregate themselves in building blocks, then what are the properties of such blocks. We propose the mental objects block as the representing structure of a concept in a neural network. We show how the local application of Hebb's law at the cell level leads to the concept of functional organization cost at the network level (upward effect), which explains spontaneous reorganization of mental blocks (downward effect). In this model, the simple hebbian learning paradigm appears to have emergent effects in both upward and downward directions." altloc: - http://perso.wanadoo.fr/christophe.lecerf/HTML_VI-DYNN98/VI-DYNN.html chapter: ~ commentary: ~ commref: ~ confdates: '1998, June 22-26' conference: VI-DYNN'98 confloc: 'Stockholm, Sweden' contact_email: ~ creators_id: [] creators_name: - family: Lecerf given: Christophe honourific: '' lineage: '' date: 1998 date_type: published datestamp: 1998-11-10 department: ~ dir: disk0/00/00/05/19 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: [] eprint_status: archive eprintid: 519 fileinfo: /style/images/fileicons/application_postscript.png;/519/1/VI%2DDYNN2W98.ps|/style/images/fileicons/application_pdf.png;/519/5/VI%2DDYNN2W98.pdf full_text_status: public importid: ~ institution: ~ isbn: ~ ispublished: inpress 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: 'reinforcement learning, associative memory, functional organizational cost' lastmod: 2011-03-11 08:54:01 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: ~ pubdom: FALSE publication: ~ publisher: SPIE refereed: FALSE referencetext: ~ relation_type: [] relation_uri: [] reportno: ~ rev_number: 14 series: ~ source: ~ status_changed: 2007-09-12 16:29:51 subjects: - comp-sci-mach-dynam-sys - comp-sci-neural-nets succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: Double Loops Flows and Bidirectional Hebb's Law in Neural Network type: confpaper userid: 92 volume: ~