update_core_Tucker: Update values in the core tensor for a Tucker model.

In nathanlazar/BaTFLED3D: Bayesian Tensor Factorization Linked to External Data

Description

Update is performed in place to avoid memory issues. There is no return value.

Usage

update_core_Tucker(m, d, params)

Arguments

m	A Tucker_model object created with mk_model
d	Input data object created with input_data
params	List of parameters created with get_model_params()

Examples

data.params <- get_data_params(c('decomp=Tucker'))
toy <- mk_toy(data.params)
train.data <- input_data$new(mode1.X=toy$mode1.X[,-1],
                             mode2.X=toy$mode2.X[,-1],
                             mode3.X=toy$mode3.X,
                             resp=toy$resp)
model.params <- get_model_params(c('decomp=Tucker'))
toy.model <- mk_model(train.data, model.params)
toy.model$rand_init(model.params)

update_core_Tucker(m=toy.model, d=train.data, params=model.params)

nathanlazar/BaTFLED3D documentation built on May 23, 2019, 12:19 p.m.