desdeo_emo.surrogatemodels.EvoDN2
¶
Module Contents¶
Functions¶
|
-
class
desdeo_emo.surrogatemodels.EvoDN2.
EvoDN2
(num_subnets: int = 4, num_subsets: int = 4, max_layers: int = 4, max_nodes: int = 4, p_omit: float = 0.2, w_low: float = - 5.0, w_high: float = 5.0, subsets: list = None, activation_function: str = 'sigmoid', loss_function: str = 'mse', training_algorithm: desdeo_emo.EAs.BaseEA.BaseEA = PPGA, pop_size: int = 500, model_selection_criterion: str = 'min_error', verbose: int = 0)[source]¶ Bases:
desdeo_problem.surrogatemodels.SurrogateModels.BaseRegressor
Helper class that provides a standard way to create an ABC using inheritance.
-
_model_performance
(self, individuals: numpy.ndarray = None, X: numpy.ndarray = None, y_true: numpy.ndarray = None)[source]¶
-
_calculate_linear
(self, previous_layer_output)[source]¶ Calculate the final layer using LLSQ or
- Parameters
non_linear_layer (np.ndarray) – Output of the activation function
- Returns
linear_layer (np.ndarray) – The optimized weight matrix of the upper part of the network
predicted_values (np.ndarray) – The prediction of the model
-