Wefirstperformsecond-orderexpansionsfor`andQalongthesolutionpath,whicharegivenby ` `(t,xt,ut) +` xTδxt +` uTδut + 1 2 δxt δut

Forinstance,consider the propagation of afully-connected layer,i.e. Let u t u (t) be a solution that achieved the minimumof(18). In our case, we consider the linear ODE presentedin(22). Let us start from the terminal condition in (29). With these, we arrive at the second-order feedbackpolicypresentedin(16).