C |
calc [Interfaces.Sigs.Deriv.Deriv.Trained] |
calc model ~targets
|
calc [Interfaces.Sigs.Deriv.Deriv.Model] |
calc inputs ~sigma2
|
calc [Interfaces.Sigs.Deriv.Deriv.Inputs] |
calc inducing points
|
calc [Interfaces.Sigs.Deriv.Deriv.Inducing] |
calc kernel inducing_points
|
calc [Interfaces.Sigs.Eval.Cov_sampler] |
calc ?predictive mean variance
|
calc [Interfaces.Sigs.Eval.Sampler] |
calc ?predictive mean variance
|
calc [Interfaces.Sigs.Eval.Covariances] |
calc co_variance_predictor ~sigma2 inputs
|
calc [Interfaces.Sigs.Eval.Variances] |
calc co_variance_predictor ~sigma2 inputs
|
calc [Interfaces.Sigs.Eval.Variance] |
calc co_variance_predictor ~sigma2 input
|
calc [Interfaces.Sigs.Eval.Co_variance_predictor] |
calc kernel inducing_points co_variance_coeffs
|
calc [Interfaces.Sigs.Eval.Means] |
calc mean_predictor inputs
|
calc [Interfaces.Sigs.Eval.Mean] |
calc mean_predictor input
|
calc [Interfaces.Sigs.Eval.Mean_predictor] |
calc inducing_points ~coeffs
|
calc [Interfaces.Sigs.Eval.Stats] |
calc trained
|
calc [Interfaces.Sigs.Eval.Trained] |
calc model ~targets
|
calc [Interfaces.Sigs.Eval.Model] |
calc inputs ~sigma2
|
calc [Interfaces.Sigs.Eval.Inputs] |
create points inducing
|
calc [Interfaces.Sigs.Eval.Input] |
calc inducing point
|
calc [Interfaces.Sigs.Eval.Inducing] |
calc kernel inducing_points
|
calc_co_variance_coeffs [Interfaces.Sigs.Eval.Model] |
calc_co_variance_coeffs model
|
calc_cross [Interfaces.Specs.Eval.Inputs] |
calc_cross kernel ~inputs ~inducing
|
calc_deriv_cross [Interfaces.Specs.Deriv.Inputs] |
calc_deriv_cross cross hyper
|
calc_deriv_diag [Interfaces.Specs.Deriv.Inputs] |
calc_deriv_diag diag hyper
|
calc_deriv_upper [Interfaces.Specs.Deriv.Inducing] |
calc_deriv_upper upper hyper
|
calc_diag [Interfaces.Specs.Eval.Inputs] |
calc_diag kernel inputs
|
calc_eval [Interfaces.Sigs.Deriv.Deriv.Trained] |
calc_eval trained
|
calc_eval [Interfaces.Sigs.Deriv.Deriv.Model] |
calc_eval model
|
calc_eval [Interfaces.Sigs.Deriv.Deriv.Inputs] |
calc_eval inputs
|
calc_eval [Interfaces.Sigs.Deriv.Deriv.Inducing] |
calc_eval inducing
|
calc_log_evidence [Interfaces.Sigs.Deriv.Deriv.Trained] |
calc_log_evidence hyper_t hyper
|
calc_log_evidence [Interfaces.Sigs.Deriv.Deriv.Model] |
calc_log_evidence hyper_t hyper
|
calc_log_evidence [Interfaces.Sigs.Eval.Trained] |
calc_log_evidence trained
|
calc_log_evidence [Interfaces.Sigs.Eval.Model] |
calc_log_evidence model
|
calc_log_evidence_sigma2 [Interfaces.Sigs.Deriv.Deriv.Trained] |
calc_log_evidence_sigma2 trained
|
calc_log_evidence_sigma2 [Interfaces.Sigs.Deriv.Deriv.Model] |
calc_log_evidence_sigma2 model
|
calc_mad [Interfaces.Sigs.Eval.Stats] |
calc_mad trained
|
calc_maxad [Interfaces.Sigs.Eval.Stats] |
calc_mad trained
|
calc_mean_coeffs [Interfaces.Sigs.Eval.Trained] |
calc_mean_coeffs trained
|
calc_model [Interfaces.Sigs.Eval.Co_variance_predictor] |
calc_model model
|
calc_model_inputs [Interfaces.Sigs.Eval.Covariances] |
calc_model_inputs model
|
calc_model_inputs [Interfaces.Sigs.Eval.Variances] |
calc_model_inputs model
|
calc_mpi_criterion [Interfaces.Sigs.Optimizer.Optimizer] |
|
calc_mpi_deriv [Interfaces.Sigs.Optimizer.Optimizer] |
|
calc_mse [Interfaces.Sigs.Eval.Stats] |
calc_mse trained
|
calc_msll [Interfaces.Sigs.Eval.Stats] |
calc_msll trained
|
calc_n_samples [Interfaces.Sigs.Eval.Stats] |
calc_n_samples trained
|
calc_rmse [Interfaces.Sigs.Eval.Stats] |
calc_sse trained
|
calc_shared_cross [Interfaces.Specs.Deriv.Inputs] |
calc_shared_cross kernel ~inputs ~inducing
|
calc_shared_diag [Interfaces.Specs.Deriv.Inputs] |
calc_shared_diag kernel inputs
|
calc_shared_upper [Interfaces.Specs.Deriv.Inducing] |
calc_shared_upper kernel inducing
|
calc_smse [Interfaces.Sigs.Eval.Stats] |
calc_smse trained
|
calc_sse [Interfaces.Sigs.Eval.Stats] |
calc_sse trained
|
calc_target_variance [Interfaces.Sigs.Eval.Stats] |
calc_target_variance trained
|
calc_trained [Interfaces.Sigs.Eval.Mean_predictor] |
calc_trained trained
|
calc_upper [Interfaces.Specs.Eval.Inputs] |
calc_upper kernel inputs
|
calc_upper [Interfaces.Specs.Eval.Inducing] |
calc_upper kernel inducing
|
check_deriv_hyper [Interfaces.Sigs.Deriv.Deriv.Test] |
check_deriv_hyper ?eps ?tol kernel inducing_points points hyper
will raise Failure if the derivative code provided in the
specification of the covariance function given parameter hyper ,
the kernel , inducing_points and input points exceeds the
tolerance tol when compared to finite differences using epsilon
eps .
|
check_sparse_col_mat_sane [Gpr_utils] |
|
check_sparse_row_mat_sane [Gpr_utils] |
|
check_sparse_vec_sane [Gpr_utils] |
|
cholesky_jitter [Gpr_utils] |
|
choose_cols [Gpr_utils] |
|
choose_n_first_inputs [Interfaces.Sigs.Eval.Inducing] |
choose_n_first_inputs kernel inputs ~n_inducing
|
choose_n_random_inputs [Interfaces.Sigs.Eval.Inducing] |
choose_n_random_inputs ?rnd_state kernel inputs ~n_inducing
|
choose_subset [Interfaces.Specs.Eval.Inputs] |
choose_subset inputs indexes
|
copy [Block_diag] |
copy bm
|
create [Cov_se_fat.Params] |
|
create [Block_diag] |
create mats
|
create [Interfaces.Sigs.Optimizer.Optimizer] |
|
create [Interfaces.Sigs.Deriv.Deriv.Optim.SMD] |
|
create [Interfaces.Sigs.Deriv.Deriv.Optim.SGD] |
|
create [Interfaces.Specs.Eval.Inputs] |
create inputs
|
create [Interfaces.Specs.Kernel] |
create params
|
create [Gpr_utils.Int_vec] |
|
create_default_kernel [Interfaces.Sigs.Eval.Inputs] |
create_default_kernel points
|
create_default_kernel_params [Interfaces.Specs.Eval.Inputs] |
create_default_kernel_params inputs ~n_inducing
|
create_inducing [Interfaces.Specs.Eval.Inputs] |
create_inducing kernel inputs
|
D |
debug [Gpr_utils] |
|
default_rng [Gpr_utils] |
|
dim [Gpr_utils.Int_vec] |
|
E |
eval [Interfaces.Specs.Eval.Input] |
eval kernel input inducing
|
eval_one [Interfaces.Specs.Eval.Input] |
eval_one kernel point
|
G |
get [Interfaces.Sigs.Eval.Covariances] |
get ?predictive covariances
|
get [Interfaces.Sigs.Eval.Variances] |
get ?predictive variances
|
get [Interfaces.Sigs.Eval.Variance] |
get ?predictive variance
|
get [Interfaces.Sigs.Eval.Means] |
get means
|
get [Interfaces.Sigs.Eval.Mean] |
get mean
|
get_all [Interfaces.Specs.Deriv.Hyper] |
get_all kernel inducing inputs
|
get_coeffs [Interfaces.Sigs.Eval.Mean_predictor] |
get_coeffs mean_predictor
|
get_eta [Interfaces.Sigs.Deriv.Deriv.Optim.SMD] |
|
get_eta [Interfaces.Sigs.Deriv.Deriv.Optim.SGD] |
|
get_inducing [Interfaces.Sigs.Eval.Mean_predictor] |
get_inducing mean_predictor
|
get_inducing [Interfaces.Sigs.Eval.Model] |
get_inputs model
|
get_inputs [Interfaces.Sigs.Eval.Model] |
get_inputs model
|
get_kernel [Interfaces.Sigs.Eval.Model] |
get_kernel model
|
get_model [Interfaces.Sigs.Eval.Trained] |
get_model trained
|
get_n_points [Interfaces.Specs.Eval.Inputs] |
get_n_points inputs
|
get_n_points [Interfaces.Specs.Eval.Inducing] |
get_n_points inducing
|
get_nu [Interfaces.Sigs.Deriv.Deriv.Optim.SMD] |
|
get_params [Interfaces.Specs.Kernel] |
get_params kernel
|
get_points [Interfaces.Sigs.Eval.Inputs] |
get_points kernel inputs
|
get_points [Interfaces.Sigs.Eval.Inducing] |
get_points kernel inducing
|
get_sigma2 [Interfaces.Sigs.Eval.Model] |
get_sigma2 model
|
get_step [Interfaces.Sigs.Deriv.Deriv.Optim.SGD] |
|
get_targets [Interfaces.Sigs.Eval.Trained] |
get_targets trained
|
get_trained [Interfaces.Sigs.Deriv.Deriv.Optim.SMD] |
|
get_trained [Interfaces.Sigs.Deriv.Deriv.Optim.SGD] |
|
get_value [Interfaces.Specs.Optimizer.Inputs] |
get_value inputs var
|
get_value [Interfaces.Specs.Optimizer.Input] |
get_value input var
|
get_value [Interfaces.Specs.Deriv.Hyper] |
get_value kernel inducing inputs hyper
|
get_variances [Interfaces.Sigs.Eval.Covariances] |
get_variances covariances
|
get_vars [Interfaces.Specs.Optimizer.Inputs] |
get_vars inputs
|
get_vars [Interfaces.Specs.Optimizer.Input] |
get_vars input
|
gradient_norm [Interfaces.Sigs.Deriv.Deriv.Optim.SMD] |
|
gradient_norm [Interfaces.Sigs.Deriv.Deriv.Optim.SGD] |
|
I |
ichol [Gpr_utils] |
|
L |
learn [Interfaces.Sigs.Optimizer.Optimizer] |
|
log_2pi [Gpr_utils] |
|
log_det [Gpr_utils] |
|
P |
pi [Gpr_utils] |
|
potrf [Block_diag] |
potrf ?jitter bm perform Cholesky factorization on block diagonal matrix
bm using Cholesky jitter if given.
|
potri [Block_diag] |
potri ?jitter ?factorize bm invert block diagonal matrix bm using
its Cholesky factor.
|
prepare_hyper [Interfaces.Sigs.Deriv.Deriv.Trained] |
prepare_hyper trained
|
prepare_hyper [Interfaces.Sigs.Deriv.Deriv.Model] |
prepare_hyper model
|
print_float [Gpr_utils] |
|
print_int [Gpr_utils] |
|
print_mat [Gpr_utils] |
|
print_vec [Gpr_utils] |
|
S |
sample [Interfaces.Sigs.Eval.Cov_sampler] |
sample ?rng sampler
|
sample [Interfaces.Sigs.Eval.Sampler] |
sample ?rng sampler
|
samples [Interfaces.Sigs.Eval.Cov_sampler] |
samples ?rng sampler ~n
|
samples [Interfaces.Sigs.Eval.Sampler] |
samples ?rng sampler ~n
|
self_test [Interfaces.Sigs.Deriv.Deriv.Test] |
self_test ?eps ?tol kernel inducing_points points ~sigma2 ~targets
hyper will raise Failure if the internal derivative code for the
log evidence given parameter hyper , the kernel ,
inducing_points , input points , noise level sigma2 and
targets exceeds the tolerance tol when compared to finite
differences using epsilon eps .
|
set_values [Interfaces.Specs.Optimizer.Inputs] |
set_values inputs vars values
|
set_values [Interfaces.Specs.Optimizer.Input] |
set_values input vars values
|
set_values [Interfaces.Specs.Deriv.Hyper] |
set_values kernel inducing inputs hypers values
|
solve_tri [Gpr_utils] |
|
step [Interfaces.Sigs.Deriv.Deriv.Optim.SMD] |
|
step [Interfaces.Sigs.Deriv.Deriv.Optim.SGD] |
|
sub [Gpr_utils.Int_vec] |
|
sum_mat [Gpr_utils] |
|
sum_symm_mat [Gpr_utils] |
|
symm2_sparse_trace [Gpr_utils] |
|
T |
test [Interfaces.Sigs.Deriv.Deriv.Optim.SMD] |
|
test [Interfaces.Sigs.Deriv.Deriv.Optim.SGD] |
|
timing [Gpr_utils] |
|
train [Interfaces.Sigs.Deriv.Deriv.Optim.Gsl] |
train ?step ?tol ?epsabs ?report_trained_model
?report_gradient_norm ?kernel ?sigma2 ?inducing ?n_rand_inducing
?learn_sigma2 ?hypers ~inputs ~targets () takes the optional
initial optimizer step size step , the optimizer line search
tolerance tol , the minimum gradient norm epsabs to achieve by
the optimizer, callbacks for reporting intermediate results
report_trained_model and report_gradient_norm , an optional
kernel , noise level sigma2 , inducing inputs inducing , number
of randomly chosen inducing inputs n_rand_inducing , a flag for
whether the noise level should be learnt learn_sigma2 , an array
of optional hyper parameters hypers which should be optimized,
and the inputs and targets .
|
U |
update_sigma2 [Interfaces.Sigs.Deriv.Deriv.Model] |
update_sigma2 model sigma2
|
update_sigma2 [Interfaces.Sigs.Eval.Model] |
update_sigma2 model sigma2
|
V |
version [Version] |
|
W |
weighted_eval [Interfaces.Specs.Eval.Inputs] |
weighted_eval kernel ~inputs ~inducing ~coeffs
|
weighted_eval [Interfaces.Specs.Eval.Input] |
weighted_eval kernel input inducing ~coeffs
|