It's time to stop making t-SNE & UMAP plots. In a new preprint w/ Tara Chari we show that while they display some correlation with the underlying high-dimension data, they don't preserve local or global structure & are misleading. They're also arbitrary.🧵https://t.co/XkAOTKlOcs https://t.co/dmFzD5RR6R

- 8월 28, 2021

Favorite tweet:

It's time to stop making t-SNE & UMAP plots. In a new preprint w/ Tara Chari we show that while they display some correlation with the underlying high-dimension data, they don't preserve local or global structure & are misleading. They're also arbitrary.🧵https://t.co/XkAOTKlOcs https://t.co/dmFzD5RR6R
— Lior Pachter (@lpachter) Aug 27, 2021

It's time to stop making t-SNE & UMAP plots. In a new preprint w/ Tara Chari we show that while they display some correlation with the underlying high-dimension data, they don't preserve local or global structure & are misleading. They're also arbitrary.🧵https://t.co/XkAOTKlOcs https://t.co/dmFzD5RR6R http://twitter.com/lpachter/status/1431325969411821572 https://t.co/XkAOTKlOcs August 28, 2021 at 03:41AM

이 블로그 검색

Scrap

댓글

댓글 쓰기

이 블로그의 인기 게시물

The TRB Forum on Preparing for Automated Vehicles and Shared Mobility brings together public, private, & research organizational partners to share perspectives on the critical issues around #AutomatedVehicles and #SharedMobility. Join us May 13! https://t.co/JdVG3j8grn https://t.co/MTJVp7Eng6

네이버 지도 API 길찾기 - 출발지와 도착지 입력

Supervised Clustering: How to Use SHAP Values for Better Cluster Analysis https://t.co/7WKYgRUJou #AI #MachineLearning #DeepLearning #DataScience https://t.co/oTVhwcnJ39