-
Notifications
You must be signed in to change notification settings - Fork 69
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
About cost in FunctionHO.py #17
Comments
Hello 😄 ,
|
Hi,
You can also use error rate, there is nothing wrong with it.
The cost function is to ensure a lower feature size while reducing the
error rate. (normally we set alpha = 0.99 and beta = 0.01)
Best Regards,
Jingwei Too
…On Wed, Apr 20, 2022 at 5:51 PM liansyyy ***@***.***> wrote:
Hello 😄 , num_feat is the number of features chosen, max_feat is total
features dataset has, (num_feat / max_feat) stands for the ratio of the
chosen features to total features. Using beta * (num_feat / max_feat), i
suppose, is to control the number of features we choose. If the num_feat
is too much, then cost would become bigger.
Hi good morning, I wonder what is cost code in here and what does it do?
cost = alpha * error + beta * (num_feat / max_feat)
And i know that you use error rate as fitness, but why use cost value as
fitness instead of error rate?
—
Reply to this email directly, view it on GitHub
<#17 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AHKG2GZPLD5UFNUFO35UVFDVF7HTDANCNFSM5RAU7QWQ>
.
You are receiving this because you are subscribed to this thread.Message
ID:
<JingweiToo/Wrapper-Feature-Selection-Toolbox-Python/issues/17/1103727930@
github.com>
|
Thank you 😄 |
Can we say that cost function is the upgrade version from error rate? because you say that cost function reduce the error rate.
|
Hi good morning,
I wonder what is cost code in here and what does it do?
cost = alpha * error + beta * (num_feat / max_feat)
And i know that you use error rate as fitness, but why use cost value as fitness instead of error rate?
The text was updated successfully, but these errors were encountered: