Hands-On Machine Learning for Cybersecurity

Adam gradient optimizer

model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy']) return model

We find the best hyperparameter optimizing for recall:

def print_gridsearch_scores_deep_learning(x_train_data,y_train_data): c_param_range = [0.01,0.1,1,10,100]clf = GridSearchCV(KerasClassifier(build_fn=network_builder, epochs=50, batch_size=128,  verbose=1, input_dim=29),  {"hidden_dimensions": ([10], [10, 10, 10], [100, 10])}, cv=5, scoring='recall') clf.fit(x_train_data,y_train_data)print "Best parameters set found on development set:" print print clf.bestparamsprint "Grid scores on development set:" means = clf.cv_results_['mean_test_score'] stds = clf.cv_results_['std_test_score'] for mean, std, params in zip(means, ...