--- abstract: 'Given the importance of using resources efficiently in the competition for survival, it is reasonable to think that natural evolution has discovered efficient cortical coding strategies for representing natural visual information. Sparse representations have intrinsic advantages in terms of fault-tolerance and low-power consumption potential, and can therefore be attractive for robot sensorimotor control with powerful dispositions for decision-making. Inspired by the mammalian brain and its visual ventral pathway, we present in this paper a hierarchical sparse coding network architecture that extracts visual features for use in sensorimotor control. Testing with natural images demonstrates that this sparse coding facilitates processing and learning in subsequent layers. Previous studies have shown how the responses of complex cells could be sparsely represented by a higher-order neural layer. Here we extend sparse coding in each network layer, showing that detailed modeling of earlier stages in the visual pathway enhances the characteristics of the receptive fields developed in subsequent stages. The yield network is more dynamic with richer and more biologically plausible input and output representation.' altloc: - http://www.lucs.lu.se/ftp/pub/LUCS_Studies/LUCS101/Yang.pdf chapter: ~ commentary: ~ commref: ~ confdates: 'August 4-5, 2003' conference: 'Third International Workshop on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems' confloc: 'Boston, MA, USA' contact_email: ~ creators_id: [] creators_name: - family: Yang given: Li honourific: '' lineage: '' - family: Jabri given: Marwan honourific: '' lineage: '' date: 2003 date_type: published datestamp: 2004-02-12 department: ~ dir: disk0/00/00/33/40 edit_lock_since: ~ edit_lock_until: ~ edit_lock_user: ~ editors_id: [] editors_name: - family: Prince given: Christopher G. honourific: '' lineage: '' - family: Berthouze given: Luc honourific: '' lineage: '' - family: Kozima given: Hideki honourific: '' lineage: '' - family: Bullock given: Daniel honourific: '' lineage: '' - family: Stojanov given: Georgi honourific: '' lineage: '' - family: Balkenius given: Christian honourific: '' lineage: '' eprint_status: archive eprintid: 3340 fileinfo: /style/images/fileicons/application_pdf.png;/3340/1/Yang.pdf 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: 'hierarchical sparse coding network, visual ventral pathway, sensorimotor control' lastmod: 2011-03-11 08:55:25 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: 131-138 pubdom: TRUE publication: ~ publisher: Lund University Cognitive Studies refereed: TRUE referencetext: ~ relation_type: [] relation_uri: [] reportno: ~ rev_number: 12 series: ~ source: ~ status_changed: 2007-09-12 16:50:12 subjects: - comp-sci-mach-vis - comp-sci-neural-nets - comp-sci-robot succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: Sparse visual models for biologically inspired sensorimotor control type: confpaper userid: 3507 volume: 101