|
EmrysFilter 0.1.0
State estimation utilities in C++23 using Eigen
|
The emission model of an observation drawn from a distribution chosen by the value: the log-density of the observation under the value's distribution. More...
#include <EmrysFilter/Models/Emission.h>
Public Types | |
| using | Scalar |
| The scalar type of the log-densities. | |
Public Member Functions | |
| DensityEmission (Observation observation, DistributionOf distributionOf) | |
| The emission of observation, under the distribution distributionOf returns for each value. | |
| Observation const & | observation () const |
| template<DiscreteSpace Space> | |
| void | logLikelihoods (Space const &space, EmissionBuffer< Space, Scalar > out) const |
| Writes the observation's log-density under each value's distribution into out. | |
The emission model of an observation drawn from a distribution chosen by the value: the log-density of the observation under the value's distribution.
distributionOf maps a value's flat index to a distribution with logDensity() of the observation, such as a Gaussian per value for a hidden Markov model with continuous observations. It may return a reference into the caller's own list of distributions or build one on the spot.
| Observation | the observation's type |
| DistributionOf | the callable from a value's flat index to its distribution |
| using Emrys::DensityEmission< Observation, DistributionOf >::Scalar |
The scalar type of the log-densities.
|
inlinenodiscard |