View Single Post
  #2  
Old 10-12-2012, 02:26 PM
magdon's Avatar
magdon magdon is offline
RPI
 
Join Date: Aug 2009
Location: Troy, NY, USA.
Posts: 595
Default Re: About the Problem 3.17b

\hat E_1 is a function of \Delta u,\Delta v. You want to choose \Delta u,\Delta v (the vector to move in) to minimize \hat E_1. The negative gradient direction is going to be the direction to move (this is shown in the chapter) and you have to rescale that so the step size is 0.5.

Quote:
Originally Posted by rpistu View Post
I don’t quite understand the Problem 3.17b. What the meaning of minimize E1 over all possible (∆u, ∆v). Instead, I think it should minimize E(u+∆u,v+∆v), starting from the point (u,v)=(0,0). Is the optimal column vector [∆u,∆v]T is corresponding to the vt in the gradient descent algorithm (here, as the problem said, it is -∆E(u,v)), the norm ||(∆u,∆v)||=0.5 corresponding to the step size ɧ, and (u,v) corresponding to the weight vector w? Then, what the meaning of compute the optimal (∆u, ∆v)?
__________________
Have faith in probability
Reply With Quote