How Bidirectional Neural Networks could be used to predict future data while they need future data?!

In the following link I see that Bidirectional LSTM is used to predict the future data in time series. I know that a Bidirectional recurrent neural network use both past and future data, and therefore for predicting future data we need future data1! Can anyone explain me how they work when in a

Using the same data for both validation and prediction in Keras

I was reading a tutorial for time series prediction by Neural Networks. I found that this code have used the same test data in the following code for validation, and later also for prediction. history = model.fit(train_X, train_y, epochs=50, batch_size=72, validation_data=(test_X, test_y), ver

Xlabel and ylabel are not shown

plt.figure(1) plt.plot(history.history["loss"], "b", label="Mean Square Error of training") plt.plot(history.history["val_loss"], "g", label="Mean Square Error of validation") plt.legend() plt.xlabel("Epoche") plt.ylabel("Mean Square Error") plt.xlim(0,200) plt.show() plt.savefig(r"C:\Users\aheida