Skip to content

Instantly share code, notes, and snippets.

@Nithanaroy

Nithanaroy/char-encoding-versus-others.csv

Last active September 9, 2018 20:52
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save Nithanaroy/3f2eb98062b280838c907eee76f5a4f7 to your computer and use it in GitHub Desktop.
Save Nithanaroy/3f2eb98062b280838c907eee76f5a4f7 to your computer and use it in GitHub Desktop.
Download ZIP
Comparison of Character One-Hot Encoding with Embedding + Hashing encoding schemes
Raw
char-encoding-versus-others.csv
Character one-hot encoding Embedding or Bucketing
fixed length inputs variable and long inputs
low character cardinality chracter cardinality is not an issue
new values are frequent best to have visibility of entire population of inputs at design phase
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment