LFD Book Forum

LFD Book Forum (http://book.caltech.edu/bookforum/index.php)
-   The Final (http://book.caltech.edu/bookforum/forumdisplay.php?f=138)
-   -   Question 2 - Meaning of /g (http://book.caltech.edu/bookforum/showthread.php?t=1438)

TonySuarez 09-07-2012 12:48 PM

Question 2 - Meaning of /g
 
I would like to clarify the meaning of \bar{g} in question 2 of the final exam, if possible...

Suppose the polynomial model g^{(D)}(X)=(1+W_D^T X)^Q which is applied to all X in a data (sub)set D. There are N_D data subsets, indexed by d. Under this model, \bar{g} is considered to be:

\bar{g}=\overline{g^{(D)}(X)}=\frac{1}{N_D}\sum_{d=1}^{N_D} (1+W_d^T X)^Q

or

\bar{g}=(1+\overline{W}^T X)^Q

where

\overline{W}=\frac{1}{N_D}\sum_{d=1}^{N_D} W_d \qquad ?

In other words, we average the "functional form" of the function, or we average the parameters of the function over the training subsets?

Thanks in advance.

yaser 09-07-2012 01:19 PM

Re: Question 2 - Meaning of /g
 
Quote:

Originally Posted by TonySuarez (Post 5017)
In other words, we average the "functional form" of the function, or we average the parameters of the function over the training subsets?

The average of the functional form.

TonySuarez 09-07-2012 01:33 PM

Re: Question 2 - Meaning of /g
 
Quote:

Originally Posted by yaser (Post 5018)
The average of the functional form.

Thank you very much Professor.

TS


All times are GMT -7. The time now is 01:18 AM.

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.