Welcome! Log In Create A New Profile

Advanced

confused smiley Decision Tree

Posted by Rey 
Announcements Last Post
Announcement SoC Curricula 09/30/2017 01:08PM
Announcement Demarcation or scoping of examinations and assessment 02/13/2017 07:59AM
Announcement School of Computing Short Learning Programmes 11/24/2014 08:37AM
Announcement Unisa contact information 07/28/2011 01:28PM
Forums Messages New
avatar
Rey
confused smiley Decision Tree
May 25, 2011 09:33PM
Correct me if I'm wrong please:

Procedure:
1. Find entropy of entire test set
2. Find Entropy of each variable in set
3. Calculate information Gain for each entire variable set
4. Place root node of highest IG
5. Calculate IG for each variable relating to previous node
6. Add node of highest information gain to previous node or add leaf node
7. loop 5

Only add variable nodes that continue to provide information <- How do I state that in a better way
Reply Quote
avatar
PubCrawler007
confused smiley Re: Decision Tree
May 26, 2011 10:41AM
Well that looks about right - variables that does not affect the outcome of a spesific node is pointless to add.
Reply Quote
avatar
Rey
confused smiley Re: Decision Tree
May 26, 2011 06:53PM
These questions take FOREVER...I'm running out of paper.... smiling smiley
Reply Quote
avatar
PubCrawler007
confused smiley Re: Decision Tree
May 26, 2011 10:41PM
Its not the paper issue that bugs me - it is more the time issue...
Reply Quote
Newer Topic Older Topic
Sorry, only registered users may post in this forum.

Click here to login