[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums

Intermediate version (was: New Paper on Opening Replies)

Posted By: Axel Reichert
Date: Sunday, 23 April 2017, at 6:59 p.m.

In Response To: Intermediate version (was: New Paper on Opening Replies) (Art Grater)

Hi Art,


: isn't it better to find the lowest mean error instead of the lowest maximum error?

It what sense "better"? The target function for optimization tasks is arbitrary. Formally, we have a multi-objective (number of rules, maximum error, elegance of rules) optimization process for which the first two objectives should be minimized and the latter should be maximized, although this will be difficult to quantify. You could as well do an optimization with the mean error as an objective, but in this case I would prefer to have a additional constraint on the maximum error: It looks so embarrassing, if you play perfect replies but fail miserably on 31P. (-:

Best regards

Axel

Messages In This Thread

 

Post Response
Your Name:
Your E-Mail Address:
Subject:
Message:

If necessary, enter your password below:

Password:
 

 

[ View Thread ] [ Post Response ] [ Return to Index ] [ Read Prev Msg ] [ Read Next Msg ]

BGonline.org Forums is maintained by Stick with WebBBS 5.12.