(Untrained) model with derivative information
calc inputs ~sigma2
model with derivative information given inputs and noise level sigma2.
update_sigma2 model sigma2
model with derivative information by updating model with new noise level sigma2.
val calc_eval : t -> Eval.Model.tcalc_eval model
model without derivative information given model.
val calc_log_evidence_sigma2 : t -> floatcalc_log_evidence_sigma2 model
the derivative of the log evidence of model with respect to the noise level (sigma2).
prepare_hyper model
the model prepared for calculating derivatives for arbitrary hyper parameters.
val calc_log_evidence : hyper_t -> Spec.Hyper.t -> floatcalc_log_evidence hyper_t hyper
the derivative of the log evidence given prepared model hyper_t with respect to the hyper variable.