31 template class BayesTreeCliqueBase<GaussianBayesTreeClique, GaussianFactorGraph>;
32 template class BayesTree<GaussianBayesTreeClique>;
40 parentSum += clique->conditional()
43 .unaryExpr([](
double x) {
return log(x); })
64 gttic(GaussianBayesTree_optimizeGradientSearch);
VectorValues gradient(const VectorValues &x0) const
VectorValues optimizeGradientSearch() const
bool equals(const This &other, double tol=1e-9) const
EIGEN_DEVICE_FUNC const ExpReturnType exp() const
double logDeterminant(const typename BAYESTREE::sharedClique &clique)
EIGEN_DEVICE_FUNC const LogReturnType log() const
Base class for cliques of a BayesTree.
double logDeterminant() const
double error(const VectorValues &x) const
VectorValues optimizeGradientSearch() const
sharedConditional marginalFactor(Key j, const Eliminate &function=EliminationTraitsType::DefaultEliminate) const
void DepthFirstForest(FOREST &forest, DATA &rootData, VISITOR_PRE &visitorPre, VISITOR_POST &visitorPost)
double error(const VectorValues &x) const
VectorValues gradient(const VectorValues &x0) const
double logDeterminant(const GaussianBayesTreeClique::shared_ptr &clique, double &parentSum)
Templated algorithms that are used in multiple places in linear.
const mpreal sum(const mpreal tab[], const unsigned long int n, int &status, mp_rnd_t mode=mpreal::get_default_rnd())
VectorValues optimizeBayesTree(const BAYESTREE &bayesTree)
VectorValues optimize() const
VectorValues gradientAtZero() const
Chordal Bayes Net, the result of eliminating a factor graph.
set noclip points set clip one set noclip two set bar set border lt lw set xdata set ydata set zdata set x2data set y2data set boxwidth set dummy x
double determinant() const
Gaussian Bayes Tree, the result of eliminating a GaussianJunctionTree.
Matrix marginalCovariance(Key key) const
std::uint64_t Key
Integer nonlinear key type.
boost::shared_ptr< This > shared_ptr
virtual VectorValues gradientAtZero() const
bool equals(const This &other, double tol=1e-9) const