DiscreteGaussianLTIModel¶
-
class
probnum.filtsmooth.DiscreteGaussianLTIModel(dynamat, forcevec, diffmat)[source]¶ Bases:
probnum.filtsmooth.DiscreteGaussianLinearModelDiscrete Gauss-Markov models of the form x_{i+1} = N(G x_i + z, S),
Attributes Summary
ndimMethods Summary
diffusionmatrix(time, **kwargs)Evaluate S(t_i) dynamics(time, state, **kwargs)Evaluate g(t_i, x_i). dynamicsmatrix(time, **kwargs)Convenient access to dynamics matrix (alternative to “jacobian”). force(time, **kwargs)jacobian(time, state, **kwargs)Evaluate Jacobian, d_x g(t_i, x_i), of g(t_i, x_i) w.r.t. pdf(loc, time, state, **kwargs)Evaluates “future” pdf p(x_t | x_s) at loc. sample(time, state, **kwargs)Samples x_{t} ~ p(x_{t} | x_{s}) as a function of t and x_s (plus additional parameters). Attributes Documentation
-
ndim¶
Methods Documentation
-
diffusionmatrix(time, **kwargs)¶ Evaluate S(t_i)
-
dynamics(time, state, **kwargs)¶ Evaluate g(t_i, x_i).
-
dynamicsmatrix(time, **kwargs)¶ Convenient access to dynamics matrix (alternative to “jacobian”).
-
force(time, **kwargs)¶
-
jacobian(time, state, **kwargs)¶ Evaluate Jacobian, d_x g(t_i, x_i), of g(t_i, x_i) w.r.t. x_i.
-
pdf(loc, time, state, **kwargs)¶ Evaluates “future” pdf p(x_t | x_s) at loc.
-
sample(time, state, **kwargs)¶ Samples x_{t} ~ p(x_{t} | x_{s}) as a function of t and x_s (plus additional parameters).
In a discrete system, i.e. t = s + 1, s in mathbb{N}
In an ODE solver setting, one of the additional parameters would be the step size.
-