Propagates a recursive least squares error distribution of parameters, with a forgetting factor λ. More...
#include <RecursiveLeastSquaresTransform.hpp>
Inheritance diagram for OpenKalman::RecursiveLeastSquaresTransform< Scalar >:
Collaboration diagram for OpenKalman::RecursiveLeastSquaresTransform< Scalar >:
Public Member Functions | |
| RecursiveLeastSquaresTransform (const Scalar lambda=0.9995) | |
| template<typename InputDist , typename ... NoiseDists, std::enable_if_t<(distribution< InputDist > and ... and distribution< NoiseDists >) and(coordinates::compares_with< typename DistributionTraits< InputDist >::StaticDescriptor, typename DistributionTraits< NoiseDists >::StaticDescriptor >and ...), int > = 0> | |
| auto | operator() (const InputDist &x, const NoiseDists &...ns) const |
| Apply the RLS transform on an input distribution. More... | |
| template<typename InputDist , typename ... NoiseDists, std::enable_if_t<(distribution< InputDist > and ... and distribution< NoiseDists >) and(coordinates::compares_with< typename DistributionTraits< InputDist >::StaticDescriptor, typename DistributionTraits< NoiseDists >::StaticDescriptor > and ...), int > = 0> | |
| auto | transform_with_cross_covariance (const InputDist &x, const NoiseDists &...ns) const |
| Perform RLS transform, also returning the cross-covariance. More... | |
 Public Member Functions inherited from OpenKalman::internal::TransformBase< RecursiveLeastSquaresTransform< Scalar > > | |
| auto | operator() (const InputDist &x, const T &t, const Ts &...ts) const |
| Perform one or more consecutive transforms. More... | |
| auto | transform_with_cross_covariance (const InputDist &x, const T &t, const Ts &...ts) const |
| Perform one or more consecutive transforms, also returning the cross-covariance. More... | |
Detailed Description
template<typename Scalar = double>
struct OpenKalman::RecursiveLeastSquaresTransform< Scalar >
Propagates a recursive least squares error distribution of parameters, with a forgetting factor λ.
Useful for parameter estimation, where the parameter is expected to possibly drift over time
- Template Parameters
-
Scalar The scalar type.
Member Function Documentation
◆ operator()()
template<typename Scalar = double>
template<typename InputDist , typename ... NoiseDists, std::enable_if_t<(distribution< InputDist > and ... and distribution< NoiseDists >) and(coordinates::compares_with< typename DistributionTraits< InputDist >::StaticDescriptor, typename DistributionTraits< NoiseDists >::StaticDescriptor >and ...), int > = 0>
|
inline |
Apply the RLS transform on an input distribution.
Any noise distributions are treated as additive.
- Template Parameters
-
InputDist The prior distribution. NoiseDists Zero or more noise distribution.
- Returns
- The posterior distribution.
◆ transform_with_cross_covariance()
template<typename Scalar = double>
template<typename InputDist , typename ... NoiseDists, std::enable_if_t<(distribution< InputDist > and ... and distribution< NoiseDists >) and(coordinates::compares_with< typename DistributionTraits< InputDist >::StaticDescriptor, typename DistributionTraits< NoiseDists >::StaticDescriptor > and ...), int > = 0>
|
inline |
Perform RLS transform, also returning the cross-covariance.
- Template Parameters
-
InputDist The prior distribution. NoiseDists Zero or more noise distribution.
- Returns
- A tuple comprising the posterior distribution and the cross-covariance.
The documentation for this struct was generated from the following file:
- OpenKalman/transforms/RecursiveLeastSquaresTransform.hpp
