What a Deep Neural Network thinks about selfies

Re:What a Deep Neural Network thinks about selfies by misiti3780 on Sunday October 25, 2015 @08:24PM (#10449034)

One thing I always found interesting is Lecun is credited with developing covnets, but Hinton is apparently credited with scaling them and showing the world how great they are in the paper from 2012 - why was Hinton's group (Toronto) able to publish these ground breaking results before Lecun's group (NYU)

[ Parent | on HN ]

Re:What a Deep Neural Network thinks about selfies by pramodliv1 on Sunday October 25, 2015 @08:38PM (#10449065)

Geoff Hinton answers this question in episode 6 of the Talking Machines podcast. http://www.thetalkingmachines.com/blog/2015/3/13/how-machine...

Geoff Hinton had grad students who wanted to work on the problem, but Yann LeCun didn't.

"In about 2012, it should have been Yann's group, but Yann was unlucky, he didn't have a student who really wanted to do it. But we had a couple of students who wanted to do it and we took all of Yann's techniques and added some of our own."

[ Parent | on HN ]

Re:What a Deep Neural Network thinks about selfies by misiti3780 on Monday October 26, 2015 @09:43AM (#10451326)

interesting - i took the course but did not notice that - thanks!

[ Parent | on HN ]

Re:What a Deep Neural Network thinks about selfies by Houshalter on Sunday October 25, 2015 @08:41PM (#10449071)

IIRC the deep learning revolution started with pretraining and RBMs, which I believe Hinton invented.

[ Parent | on HN ]