LFD Book Forum

LFD Book Forum (http://book.caltech.edu/bookforum/index.php)
-   Chapter 5 - Three Learning Principles (http://book.caltech.edu/bookforum/forumdisplay.php?f=112)
-   -   Relative size of data set v/s test set (http://book.caltech.edu/bookforum/showthread.php?t=4534)

AnonymousMachine 10-29-2014 09:51 AM

Relative size of data set v/s test set
 
Hi -

Based on assignment 9, just wanted to understand the significance of relative size of data set and the test set.

As per assignment from a total size of 9298 data points we use only 300 data points and reserve the rest for test set.

Is there any principle/logic behind the data set size and test set size ratio. Having a data set size far less than test set size kind of baffles me.

Any thoughts?

Thanks.

magdon 10-29-2014 07:46 PM

Re: Relative size of data set v/s test set
 
THis is just to simulate learning with a small data set and the huge test set provides an accurate way to measure Eout.

Quote:

Originally Posted by AnonymousMachine (Post 11795)
Hi -

Based on assignment 9, just wanted to understand the significance of relative size of data set and the test set.

As per assignment from a total size of 9298 data points we use only 300 data points and reserve the rest for test set.

Is there any principle/logic behind the data set size and test set size ratio. Having a data set size far less than test set size kind of baffles me.

Any thoughts?

Thanks.


diethealthcare 04-08-2017 03:04 AM

Re: Relative size of data set v/s test set
 
Great information ,thanks alot.


All times are GMT -7. The time now is 04:45 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.