Thursday, October 18, 2007

Learning by computer

Okay - this is clear as mud, but I was typing while listening and then the wifi went down (again)

Internal representations:
better to let object with both A and B characteristics be represented by both A and B active rather than learning something as AB. Better for generalization.

What goals:
current focusing on image recognition
want to recognize variations of a picture of an object

starting with an end result, suppose I don't know the structure of the data
can try to build a heirarcy
N^2 algorithm

You may comment on this blog
by visiting *GHC bulletin board*.

No comments: