Building high-level features using large scale unsupervised learning

Re:Building high-level features using large scale unsupervis... by JohnHaugeland on Friday June 22, 2012 @07:45AM (#4146342)

Let's not, because it's still wrong on the order of thirty counterexamples.

Let's say we'll stop making broad proclamations about the global best in a field we know very little about.

[ Parent | on HN ]

Re:Building high-level features using large scale unsupervis... by robrenaud on Friday June 22, 2012 @10:51AM (#4146957)

Andrew Ng has set many state of the art results on various data sets using similar approaches as the one described in the paper.

Here is a reasonably approachable talk he gave about it. http://www.youtube.com/watch?v=ZmNOAtZIgIk

[ Parent | on HN ]

Re:Building high-level features using large scale unsupervis... by JohnHaugeland on Friday June 22, 2012 @11:18AM (#4147117)

This is a very interesting talk.

Thank you for sharing with me. :)

In return, I will offer you two interesting non-sequiturs, because I don't have anything topical and a non-sequitur seems like it's worth half what something germane would be.

Bret Victor, "Inventing on Principle." First 5 minutes are terribly boring. Give him a chance; it's 100% worth it.

http://vimeo.com/36579366

Damian Conway, "Temporally Quaquaversal Virtual Nanomachine."

It's as funny as it sounds.

http://yow.eventer.com/events/1004/talks/1028

[ Parent | on HN ]