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 marshallp on Friday June 22, 2012 @02:07AM (#4145659)
If the algorithm keeps increasing in accuracy as you scale up computation and add more unlabeled data that is pretty amazing. You might get something that matches human performance on vision/speech recognition etc.
[ Parent | on HN ]
Re:Building high-level features using large scale unsupervis... by jules on Friday June 22, 2012 @08:10AM (#4146410)
If you extrapolate that way you'd conclude that naive Bayes is the solution to AI. Improvements tend to tail off fairly quickly as you add more data and computation, unfortunately.
[ Parent | on HN ]