6. Consider below training error and test error observed as we train for a neural network using batch gradient descent. Error versus Weight Updates (Example 1) Training set error Validation sel error Error 0.01 0.009 0.008 0.007 0.006 0.005 0.004 0.003 0.X2 0 5000 10000 15000 Number of weight updates 20000 1) 13 pts) is there overfitting with the trained model? How do you know? 2) (3 pts) i) If we double the size of the training data, plot the new curves (on the figure together with the old curves) for training error and testing error, respectively. 15 pts) ii) Briefly explain why we may have such new curves