Cool idea. Here's how to solve it (if solvable). https://www.kaggle.com/c/decoding-the-human-brain …
Seeing a lot of misinterpretation here --this is not mind reading, just deliberate keyboard input. Like swipe keyboards, but with EEG/MEG.https://twitter.com/fchollet/status/811394648337838080 …
-
-
-
amusingly I'm on that leaderboard
- Show replies
New conversation -
-
-
moving a cursor, as in swipe kb, seems plausible with eeg. There are studies. But obviously it is slower than thought, as swipe
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
isn't that what the p300 speller does, e.g. Stephen hawking?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
would be super hard to correct mistakes if it's not mind reading.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
A querty keyboard isn't the way to go imho. A stenograph would be closer, but there is most likely an optimal info theoretic way
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
reading intent to use fine motor skills without haptic feedback is going to be really bad.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
how different would be to think of letters/words for that keyboard than your usual thinking? I suspect it would be just the same.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
.
@fchollet This IS mind reading using MEG. It isn't practical (obviously), but it was a fun proof-of-concept! https://www.ncbi.nlm.nih.gov/pubmed/22565201 pic.twitter.com/l7b0UTT6cm
-
.
@fchollet Mind reading much easier w/ fMRI than MEG. Able to distinguish thought of "bear" vs "dog" via brain data. http://www.cs.cmu.edu/~fmri/papers/zero-shot-learning.pdf …pic.twitter.com/oY7M6KZD45
- Show replies
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.