metamod.ANN module

Custom ANN definition.

This module contains the definition of an ANN comptable with the SMT Toolbox.

class metamod.ANN.ANN_base(**kwargs)

Bases: smt.surrogate_models.surrogate_model.SurrogateModel

ANN general class.

tbd

Settings to be declared.

Type:dict_keys

log_dir

Directory to store the ANN model.

Type:str

validation_points

Validation points.

Type:dict

optimized

Whether the hyperparameters have been optimized.

Type:bool

set_validation_values(xt, yt, name=None)

Set validation data (values).

Parameters:

• xt (np.ndarray[nt, nx] or np.ndarray[nt]) – The input values for the nt training points.
• yt (np.ndarray[nt, ny] or np.ndarray[nt]) – The output values for the nt training points.
• name (str or None) – An optional label for the group of training points being set. This is only used in special situations (e.g., multi-fidelity applications).

write_stats(dictionary_as_list, name)

Writes the statistics about the surrogate’s training.

Parameters:

• dictionary_as_list (list) – Training statistics.
• name (str) – Name of the file to be written.