5
$\begingroup$

I'm relatively new to neural networks and was wondering what an implementation of this paper would look like. More specifically, how are the correct values of Kp, Ki, and Kd determined at run time so it can be back propagated?

$\endgroup$
  • $\begingroup$ Very cool topic (re: NNPID-based Adaptive Control for Electro-Optical Gyro Stabilized Platform :) Welcome to AI! $\endgroup$ – DukeZhou Sep 5 '17 at 20:55
1
$\begingroup$

In the paper there is a diagram of the network showing how there are 3 outputs which share features but have their own set of associated weights. Back propagation works by only looking at one output at a time. Network Architecture

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.