e best) classification accuracy via an architecture with so much biological realism. Itamar's architecture, like that of Jeff Hawkins (but unlike Poggio's), does not aspire to detailed biological realism. This allows it to use recurrent connections (which Poggio doesn't use in his architecture yet s

onnections of the visual cortex; and it's not actually the highest-accuracy video or image classifier currently available.... The novel thing about Poggio's approach isn't so much its classification accuracy (which is not the best) but the fact that it achieves GOOD (even if not the best) classificat

like that of Jeff Hawkins (but unlike Poggio's), does not aspire to detailed biological realism. This allows it to use recurrent connections (which Poggio doesn't use in his architecture yet so far as I know, probably because we don't yet know how recurrent connections work in the visual cortex, and P

e best) classification accuracy via an architecture with so much biological realism. Itamar's architecture, like that of Jeff Hawkins (but unlike Poggio's), does not aspire to detailed biological realism. This allows it to use recurrent connections (which Poggio doesn't use in his architecture yet s

onnections of the visual cortex; and it's not actually the highest-accuracy video or image classifier currently available.... The novel thing about Poggio's approach isn't so much its classification accuracy (which is not the best) but the fact that it achieves GOOD (even if not the best) classificat

like that of Jeff Hawkins (but unlike Poggio's), does not aspire to detailed biological realism. This allows it to use recurrent connections (which Poggio doesn't use in his architecture yet so far as I know, probably because we don't yet know how recurrent connections work in the visual cortex, and P

ns and his employees ;-) I.e., he is extremely sure he has the One True Path ... far more so than all the rest of us egomaniacs.... I doubt that Poggio knows about Itamar's work, but I suspect he would like it. Regarding perception processing, Itamar has the same basic philosophy as Poggio ... the

oubt that Poggio knows about Itamar's work, but I suspect he would like it. Regarding perception processing, Itamar has the same basic philosophy as Poggio ... the difference is that Poggio is focusing on brain modeling whereas Itamar is trying to build AGI. Which allows Itamar to insert architectural

known. At the Industry Day for the DARPA Deep Learning BAA (a few months ago), Itamar and I talked to the guys who are working on commercializing Poggio's stuff for image and video classification, and they said they are having a lot of trouble getting good results on practical problems. But Poggio h

onnections of the visual cortex; and it's not actually the highest-accuracy video or image classifier currently available.... The novel thing about Poggio's approach isn't so much its classification accuracy (which is not the best) but the fact that it achieves GOOD (even if not the best) classificati

like that of Jeff Hawkins (but unlike Poggio's), does not aspire to detailed biological realism. This allows it to use recurrent connections (which Poggio doesn't use in his architecture yet so far as I know, probably because we don't yet know how recurrent connections work in the visual cortex, and P

o doesn't use in his architecture yet so far as I know, probably because we don't yet know how recurrent connections work in the visual cortex, and Poggio is committed to biological realism). Actually, I think the "secret sauce" of AGI lies in cognition not vision ... but I also think that it's great

To: Ben Goertze Cc: Jeffrey E stein [email protected] From: on behalf of Itamar Arel Sent Sat 10/10/2009 8:41:14 PM Subject Comparison to Poggio's work One of Poggio's students recently published his Ph.D. which is centered on hierarchical learning methods for vision and speech (see: http:/

Jeffrey E stein [email protected] From: on behalf of Itamar Arel Sent Sat 10/10/2009 8:41:14 PM Subject Comparison to Poggio's work One of Poggio's students recently published his Ph.D. which is centered on hierarchical learning methods for vision and speech (see: http://web.mit.edu/jvb/www/p

t in my long reply is that for AGI we don't just need an accurate vision system, we need one that integrates well with a cognition system. Actually Poggio's systems and Itamar's are both OK in that regard (unlike, say, an SVM based vision system) .. they're both hierarchical recurrent NN architectures