Much better sensors. The consumer grade hardware available now doesn't come close.
Modern deep learning (esp. transfer learning) has the potential to solve this, but first we will need far better sensors.https://twitter.com/fchollet/status/811394648337838080 …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
A huge opportunity. But immediate privacy concern is thoughts you don't want recorded might be accessible to companies.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Agree, we lack non-invasive EEG with high accuracy.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Sensor progress likely to be driven (at least near term) by neural control of prosthetics; lots of R&D, starting to show successes
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
seems like this would benefit from an intermediate step. Requires coadaptation between user and machine, practice on s.t. easier
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
even invasive eeg (ecog) doesn't allow reading the inner talk, the flow of thought. Maybe few electrodes at specific region. maybe
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I can't imagine this will be possible without internal sensors, skull attenuation too great. Neural mesh will take decade or more
-
deep learning can't create data from noise
End of conversation
New conversation -
-
-
Non-invasive BMI of that sort seems hard. I don't know if it would be possible anytime soon
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
mind control with deep learning?
#feelthelearn#torchedThanks. Twitter will use this to make your timeline better. UndoUndo
-
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.