Very interesting work, thank you! I've got one question: You recommend using the maxLikGlobalDimEst() function from the intrinsicDimension package to estimate the dimensionality of the data and determine the number of PCs to include in downstream steps. 1/n
-
-
-
However, that function itself takes k as an argument. When plotting the result of maxLikGlobalDimEst() over k, I get roughly the same shape as the variability explained by each PC. Do you have advice on how do to choose a proper value for k? Thank you! 2/2pic.twitter.com/tIwlwNuIya
- Još 3 druga odgovora
Novi razgovor -
-
-
Happy to see your PhD is going well! ;)
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
-
-
Like the sticker!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.