desdeo_emo.surrogatemodels.EvoNN

Module Contents

Classes

EvoNN

Helper class that provides a standard way to create an ABC using

Functions

negative_r2_score(y_true, y_pred)

desdeo_emo.surrogatemodels.EvoNN.negative_r2_score(y_true, y_pred)[source]
class desdeo_emo.surrogatemodels.EvoNN.EvoNN(num_hidden_nodes: int = 20, p_omit: float = 0.2, w_low: float = -5.0, w_high: float = 5.0, activation_function: str = 'sigmoid', loss_function: str = 'mse', training_algorithm: Type[desdeo_emo.EAs.BaseEA.BaseEA] = PPGA, pop_size: int = 500, model_selection_criterion: str = 'akaike_corrected', recombination_type: str = 'evonn_xover_mutation', crossover_type: str = 'standard', mutation_type: str = 'gaussian')[source]

Bases: desdeo_problem.surrogatemodels.SurrogateModels.BaseRegressor

Helper class that provides a standard way to create an ABC using inheritance.

fit(X: numpy.ndarray, y: numpy.ndarray)[source]
_model_performance(first_layer: numpy.ndarray = None, X: numpy.ndarray = None, y_true: numpy.ndarray = None)[source]
predict(X: numpy.ndarray = None, first_layer: numpy.ndarray = None, training: bool = False)[source]
activate(x)[source]
calculate_linear(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

  • training_error (float) – The model’s training error

_create_individuals()[source]
select()[source]