News for hackers. Stuff that matters.

A comment on Building high-level features using large scale unsupervised learning. Parent comment

Re:Building high-level features using large scale unsupervis... by frisco on Friday June 22, 2012 @02:11AM (#4145665)
> This is the most powerful AI experiment yet conducted (publicly known).

That's an ill-defined statement. AI is a vast and diverse field: what makes one demonstration more "powerful" than another? There are definitely other projects that could be viewed as being in the same class of "powerful" as this cluster.

This is certainly an interesting paper, but it has to be viewed in the context of a large and active field.

[ Parent | on HN ]
Re:Building high-level features using large scale unsupervis... by marshallp on Friday June 22, 2012 @02:16AM (#4145677)
That's true. Let's say in machine learning then.
[ Parent | on HN ]
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 ]