SHAP如何解释深度信仰网络

Question

classifier = SupervisedDBNClassification(hidden_layers_structure=[100, 100, 100],
                                     learning_rate_rbm=0.05, 
                                     learning_rate=0.1, 
                                     n_epochs_rbm=10, 
                                     n_iter_backprop=100, 
                                     batch_size=20,  # 32
                                     activation_function='relu',
                                     dropout_p=0.2)
model = classifier.fit(X_train, Y_train)

explainer = shap.DeepExplainer(model, X_train)

https://github.com/albertbup/deep-belief-network

SupervisedDBNClassification来自此链接