Re:Theoretical Motivations for Deep Learning
by dnautics on Tuesday October 20, 2015 @12:58PM
(#10420327)
I wonder if "lots of data" is wrong. If I show you say twenty similar-looking Chinese characters in one person's handwriting, and the same twenty in another person's handwriting, you'll probably do a good job (though maybe not an easy time) classifying them with very little data.
[ Parent
| on HN ]
Re:Theoretical Motivations for Deep Learning
by webmasterraj on Wednesday October 21, 2015 @03:23PM
(#10427919)
Because I've seen lots of other handwriting, even if in another language. I have very strong priors.
The problem is that a computer comes in without knowing anything about tangential phenomenon. So it needs lots of data to catch up to me and my years of forming associative connections about other handwriting I've seen.
If I showed you alien (ie not human) handwritten samples, you'd probably stuggle too.
Re:Theoretical Motivations for Deep Learning
by p1esk on Tuesday October 20, 2015 @04:41PM
(#10421664)
"you'll probably do a good job classifying them with very little data."
It's because we use much better algorithms in our brains (compared to the ones we currently have in DL). Having "lots of data" allows us to get good results even while using inferior algorithms.
Re:Theoretical Motivations for Deep Learning
by Houshalter on Wednesday October 21, 2015 @06:49PM
(#10429368)
A baby who's never seen an image before wouldn't be able to do that. It wouldn't even know what writing is.