“…The function Firstly, while using the standard gradient descent method, instead of dealing with the system (2.7), one can solve the observer equations (2.19) with some initial condition M(0) ∈ Γ 0 and use then Lemma 2.2 to compute X as corresponding to M(t) for some sufficiently large t > 0. It is well known that applying the Euler method (2.8) to solve (2.7), i.e following the conventional backpropagation algorithm, leads to accumulation of a global error proportional to the step size h. At the same time, the numerical integration of the observer system (2.19), as due to the existence of the attractor set Γ 0 , is much more stable numerically since the solution is attracted by the integral manifold Γ 0 (see [6] for more details and examples).…”