LFD Book Forum  

Go Back   LFD Book Forum > Book Feedback - Learning From Data > Chapter 1 - The Learning Problem

Reply
 
Thread Tools Display Modes
  #1  
Old 09-17-2013, 06:03 PM
Sandes Sandes is offline
Junior Member
 
Join Date: Sep 2013
Posts: 2
Default Problem 1.12a

I'm somewhat lost in my attempt to show 1.12 a I can see intuitively that the mean will be the best h value since then Ein is the standard deviation, but I'm not sure where to go from there. I've already finished B and C, A is the only part I'm having trouble with.

Perhaps I'm going in the wrong direction but one of the things I realized is that the constraint could be restated as minimizing h^2 -2 h yn summed over all N but that could be going off in completely the wrong direction.

Adding some value a to the mean produces (mean-yn)^2 + a^2 +2 a(mean-yn) That's another possible approach but I'm not really sure where I would take that approach either.
Reply With Quote
  #2  
Old 09-17-2013, 09:09 PM
Sweater Monkey Sweater Monkey is offline
Junior Member
 
Join Date: Sep 2013
Posts: 6
Default Re: Problem 1.12a

Quote:
Originally Posted by Sandes View Post
Perhaps I'm going in the wrong direction but one of the things I realized is that the constraint could be restated as minimizing h^2 -2 h yn summed over all N but that could be going off in completely the wrong direction.
This is what I did and it led to the correct answer of hmean

To start off work on factoring out h, then it should become more obvious how to manipulate the function to find its minimum value. Good luck!
Reply With Quote
  #3  
Old 09-18-2013, 07:35 PM
meixingdg meixingdg is offline
Junior Member
 
Join Date: Sep 2013
Posts: 4
Default Re: Problem 1.12a

I tried to take the derivative of the function to find the minimum, but I'm still not sure how the minimum corresponds to h being the in-sample mean.
Also, what exactly is hmean? It seems to be a scalar value, a number of some sort, but I thought that h is a hypothesis/function?
Reply With Quote
  #4  
Old 09-19-2013, 03:55 AM
magdon's Avatar
magdon magdon is offline
RPI
 
Join Date: Aug 2009
Location: Troy, NY, USA.
Posts: 595
Default Re: Problem 1.12a

Quote:
Originally Posted by Sandes View Post
I
Perhaps I'm going in the wrong direction but one of the things I realized is that the constraint could be restated as minimizing h^2 -2 h yn summed over all N but that could be going off in completely the wrong direction.
This is the right idea. Your hypothesis h is just a number in this case. Ein is a function of this number (variable) h. One way to minimize a function of a variable h is to take the derivative and set it to zero.
__________________
Have faith in probability
Reply With Quote
Reply

Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT -7. The time now is 05:37 PM.


Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2019, Jelsoft Enterprises Ltd.
The contents of this forum are to be used ONLY by readers of the Learning From Data book by Yaser S. Abu-Mostafa, Malik Magdon-Ismail, and Hsuan-Tien Lin, and participants in the Learning From Data MOOC by Yaser S. Abu-Mostafa. No part of these contents is to be communicated or made accessible to ANY other person or entity.