A Biological Model of Object Recognition with Feature Learning
dc.date.accessioned | 2004-10-01T14:00:10Z | |
dc.date.accessioned | 2018-11-24T10:09:39Z | |
dc.date.available | 2004-10-01T14:00:10Z | |
dc.date.available | 2018-11-24T10:09:39Z | |
dc.date.issued | 2003-06-01 | en_US |
dc.identifier.uri | http://hdl.handle.net/1721.1/5571 | |
dc.identifier.uri | http://repository.aust.edu.ng/xmlui/handle/1721.1/5571 | |
dc.description.abstract | Previous biological models of object recognition in cortex have been evaluated using idealized scenes and have hard-coded features, such as the HMAX model by Riesenhuber and Poggio [10]. Because HMAX uses the same set of features for all object classes, it does not perform well in the task of detecting a target object in clutter. This thesis presents a new model that integrates learning of object-specific features with the HMAX. The new model performs better than the standard HMAX and comparably to a computer vision system on face detection. Results from experimenting with unsupervised learning of features and the use of a biologically-plausible classifier are presented. | en_US |
dc.format.extent | 4307593 bytes | |
dc.format.extent | 5073756 bytes | |
dc.language.iso | en_US | |
dc.subject | AI | en_US |
dc.title | A Biological Model of Object Recognition with Feature Learning | en_US |
Files in this item
Files | Size | Format | View |
---|---|---|---|
AITR-2003-009.pdf | 5.073Mb | application/pdf | View/ |
AITR-2003-009.ps | 4.307Mb | application/postscript | View/ |