ensemble.deeptrafo: Deep ensembling for neural network transformation models

Description

Deep ensembling for neural network transformation models

Usage

# S3 method for deeptrafo
ensemble(
  x,
  n_ensemble = 5,
  reinitialize = TRUE,
  mylapply = lapply,
  verbose = FALSE,
  patience = 20,
  plot = TRUE,
  print_members = TRUE,
  stop_if_nan = TRUE,
  save_weights = TRUE,
  callbacks = list(),
  save_fun = NULL,
  seed = seq_len(n_ensemble),
  ...
)

Value

Ensemble of "deeptrafo" models with list of training histories and fitted weights included in ensemble_results. For details see the return statment in ensemble.

Arguments

x: Object of class "deeptrafo".
n_ensemble: Numeric; number of ensemble members to fit.
reinitialize: Logical; if TRUE (default), model weights are initialized randomly prior to fitting each member. Fixed weights are not affected.
mylapply: Function; lapply function to be used; defaults to lapply
verbose: Logical; whether to print training in each fold.
patience: Integer; number of patience for early stopping.
plot: Logical; whether to plot the resulting losses in each fold.
print_members: Logical; print results for each member.
stop_if_nan: Logical; whether to stop ensembling if NaN values occur
save_weights: Logical; whether to save the ensemble weights.
callbacks: List; callbacks used for fitting.
save_fun: Function; function to be applied to each member to be stored in the final result.
seed: Numeric vector of length n_ensemble; seeds for model initialization.
...: Further arguments passed to object$fit_fun.