-
Notifications
You must be signed in to change notification settings - Fork 6
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
LinearNetwork support for compensating for input/output synapse #125
Comments
Also note that the special case of |
Full support connected to #106. |
The network's |
Also note that it's possible to avoid needing |
Special case (for rolling window) of getting the state encoded into another ensemble while accounting for the extra filtering:
May also need to provide the same For |
There are ways to change the readout to account for extra filtering. This involves either assuming
D != 0
or\dot{u} = 0
and then computing the derivatives ofy
needed to cancel out the additional filter (this can be done analytically from the state-space representation). For example, if the extra filter isLowpass(tau)
, then the output would need to be (in the continuous case)tau*\dot{y} + y
, wherey = Cx + Du
and\dot{y} = C\dot{x} + D\dot{u}
.The text was updated successfully, but these errors were encountered: