A measurement model: a function \( h \) of its input, with the policies that say what it reads, what it writes, and what it is affine in, and its noise (decisions.md [model-policies]).
More...
template<typename F, typename... Policies>
class Emrys::MeasurementFunction< F, Policies >
A measurement model: a function \( h \) of its input, with the policies that say what it reads, what it writes, and what it is affine in, and its noise (decisions.md [model-policies]).
measurementModel() builds one; a user never spells the type. The function is called as h(in, out, x), h(in, x), or h(x), whichever it takes, with in the instance of the input space that reads() defines, or the state's space without reads(), out the instance of the output space, and x a vector in in, which it reads with block<Name>(in, x); it returns a vector in out, which it may fill block by block from zeros<T>(out), either generic in its scalar or with its Jacobian beside it (withJacobian(), decisions.md [returned-jacobians]). A function generic in its scalar may take it as its one template parameter, []<typename T>(auto const & in, auto const & out, auto const &
x), which the call supplies (decisions.md [function-scalars]). A model with a likelihood alone (logLikelihood()) and no function serves the filters that weight points.
- Template Parameters
-
| F | the function, or internal::NoFunction |
| Policies | the policies, each at most once |
- See also
- measurementModel(), observe(), MeasurementModel
1.18.0