View Single Post
  #2  
Old 06-20-2015, 12:17 AM
yaser's Avatar
yaser yaser is offline
Caltech
 
Join Date: Aug 2009
Location: Pasadena, California, USA
Posts: 1,477
Default Re: Noisy target - problem in understanding distribution

Quote:
Originally Posted by iamds View Post
I am not able to understand how is no loss in generality ensured by considering target distribution and not target function ?
If we can express a function as a distribution, then considering only distributions will not exclude functions, hence there would be no loss in generality. The fact that we can indeed express a function f({\bf x}) as a distribution P(y|{\bf x}) is based on using a "delta function" which allows distributions to put all the probability on a single value of y, thus making it effectively a function since y is uniquely determined by {\bf x}.
__________________
Where everyone thinks alike, no one thinks very much
Reply With Quote