@BrianRoemmele I was thinking about your post a couple weeks ago about chunking. Would it make sense with voice recognition to predict based on most likely chunks, instead of word for word, or even further have those chunks represented (internally) with a character (like kanji)
-
-
Thank you! Just out of curiosity, would it make computation faster if chunks were represented by characters or symbols, or is that unnecessary?
-
And chunking just makes sense. It’s more efficient and it’s very similar to some association methods used by human memory masters for faster recall. There’s a definite parallel.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.