Y
Hacker News
new
|
ask
|
show
|
jobs
by
Animats
3647 days ago
"Except for the inconvenient fact that the cerebellum is not explicitly solving control theory equations."
It might be. You can invert a model by training a neural net to compute its inverse.
2 comments
argonaut
3646 days ago
It might be. It might not be. Hardly a compelling argument.
link
sharemywin
3647 days ago
reinforcement learning goes along way too.
link