[Martin Taylor 2019.12.26.11.29]
[BruceNevin 20191225.16:30ET]
…
It’s
pretty clear that updating the BCI is done by training a
neural net. The 2018 London/Göttingen hand " interpreted
the wearer’s intentions and sent commands
to the artificial limb …
it used machine
learning-based techniques [=neural nets] to interpret neural
signals from the brain to improve the performance of
prosthetic hands. " This is why they say the same
prosthetic would serve an amputee and someone with
incapacitated motor neural functions.
Ifthey make more of that subtlety available on the output
side and let the wearer’s brain do the reorganizing they’d
be closer.
…
Bruce, given that the organic arm's local control systems
participate in a normal reorganization process as the organism
(human) matures, why would you want to deny the prosthetic arm the
same possibility? Or maybe you have an alternative to a neural
network in mind?
BTW, I have not read the subject article, which may well contain a
good answer. If so, I apologize for butting in.
Martin