If you have 10,000,000 examples, how would you split the train/dev/test set?

If your Neural Network model seems to have high variance, what of the following would be promising things to try?

You are working on an automated check-out kiosk for a supermarket, and are building a classifier for apples, bananas and oranges. Suppose your classifier obtains a training set error of 0.5%, and a dev set error of 7%. How to improve your classifier?

What is weight decay?

What happens when you increase the regularization hyperparameter lambda?

With the inverted dropout technique, at test time:

Increasing the parameter keep_prob from (say) 0.5 to 0.6 will likely cause the following:

List two techniques are useful for reducing variance (reducing overfitting)?

Why do we normalize the inputs x?