Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Sabelja, Joseph"'
Autor:
Gourgoulias, Kostis, Ghalyan, Najah, Labonne, Maxime, Satsangi, Yash, Moran, Sean, Sabelja, Joseph
This paper introduces an unsupervised method to estimate the class separability of text datasets from a topological point of view. Using persistent homology, we demonstrate how tracking the evolution of embedding manifolds during training can inform
Externí odkaz:
http://arxiv.org/abs/2305.15016
Autor:
Ghalyan, Najah, Gourgoulias, Kostis, Satsangi, Yash, Moran, Sean, Labonne, Maxime, Sabelja, Joseph
This paper proposes an unsupervised method that leverages topological characteristics of data manifolds to estimate class separability of the data without requiring labels. Experiments conducted in this paper on several datasets demonstrate a clear c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::551483c55fdb5207a490cea2b1944f2b