Module gcp_bigquery_client::model::training_options
source · [−]Expand description
Options used in model training.
Structs
Enums
The data frequency of a time series.
The data split type for training and evaluation, e.g. RANDOM.
Distance type for clustering models.
Feedback type that specifies which algorithm to run for matrix factorization.
The geographical region based on which the holidays are considered in time series modeling. If a valid value is specified, then holiday effects modeling is enabled.
The method used to initialize the centroids for kmeans algorithm.
The strategy to determine learn rate for the current iteration.
Type of loss function used during training run.
Optimization strategy for training linear regression models.