Backward stepwise elimination: A model-based method for nonlinear dimension reduction

In multidimensional data modeling, dimension reduction is not intuitive. Forward feature selection is usually deceptive. That is, a strongly related feature may have a small correlation coefficient (near zero) to the objective, especially when the... continue reading

Welcome

This is the Journal of Brief Ideas - citable ideas in fewer than 200 words.

Before you can create a new idea, you'll need to log in using the link above. You also can't vote on existing ideas without signing in too.

Voting

Click on the icon to vote on an idea. You can't vote on your own ideas.