Show simple item record

dc.contributor.authorSerre, T.
dc.contributor.authorKouh, M.
dc.contributor.authorCadieu, C.
dc.contributor.authorKnoblich, U.
dc.contributor.authorKreiman, G.
dc.contributor.authorPoggio, T.
dc.date.accessioned2007-03-12T16:41:47Z
dc.date.available2007-03-12T16:41:47Z
dc.date.issued2005-12-19
dc.identifier.otherMIT-CSAIL-TR-2005-082
dc.identifier.otherAIM-2005-36
dc.identifier.otherCBCL-259
dc.identifier.urihttp://hdl.handle.net/1721.1/36407
dc.description.abstractWe describe a quantitative theory to account for the computations performed by the feedforward path of the ventral stream of visual cortex and the local circuits implementing them. We show that a model instantiating the theory is capable of performing recognition on datasets of complex images at the level of human observers in rapid categorization tasks. We also show that the theory is consistent with (and in some case has predicted) several properties of neurons in V1, V4, IT and PFC. The theory seems sufficiently comprehensive, detailed and satisfactory to represent an interesting challenge for physiologists and modelers: either disprove its basic features or propose alternative theories of equivalent scope. The theory suggests a number of open questions for visual physiology and psychophysics.
dc.format.extent130 p.
dc.relation.ispartofseriesMassachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory
dc.subjectAI
dc.subjectobject recognition
dc.subjectstandard model
dc.subjecttheory
dc.subjectvisual cortex
dc.subjectventral stream
dc.subjecthmax
dc.titleA Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record