Distance funtion of knn classifier

1 次查看（过去 30 天）
Elena Casiraghi
Elena Casiraghi 2020-4-4
Dear,none
I used Bayesian Optimization to choose the best parameters for a knn classifier.
After optimizing I got a knn with JACCARD distance and INVERSE distance weights, and no standardization.
I suppose this means that the nearest points are those that are the most distant (when using the jaccard).
Is anyone able to tell me how may I reproduce the INVERSE jaccard (with no standardization) by using the KDTreeSearcher or the ExhaustiveSearcher??
In other words, I would like to find, for each point in a test set, all the points that are the nearest, according to the distance function used by the optimized knn classifier.
THANKS a lot for any help!

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Nearest Neighbors 的更多信息

标签

产品


版本

R2019a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by