Skip to content
SMOTE: makin' yourself some fake minority data episode artwork

Jun 13, 2016 14 min

SMOTE: makin' yourself some fake minority data

from Linear Digressions Hosted by Katie Malone

Machine learning on imbalanced classes: surprisingly tricky. Many (most?) algorithms tend to just assign the majority class label to all the data and call it a day. SMOTE is an algorithm for manufacturing new minority class examples for yourself, to help your algorithm better identify them in the wild. Relevant links: https://www.jair.org/media/953/live-953-2037-jair.pdf

Episode details come from the podcast's RSS feed.

Embed this episode

Ready to play

SMOTE: makin' yourself some fake minority data

0:00 14:37

No transcript yet.

Requests help us decide what to transcribe next.

Frequently asked questions

How long is this episode of Linear Digressions?

This episode is 14 minutes long.

When was this Linear Digressions episode published?

This episode was published on June 13, 2016.

Can I download this Linear Digressions episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.