Explain in one page two different exponential advantages of deep learning over classic learning algorithms that do not use distributed representations.

First, learning distributed representations enable generalization to new combinations of the values of learned features beyond those seen during training (for example, 2n combinations are possible with n binary features)68,69.

Second, composing layers of representation in a deep net brings the potential for another exponential advantage70 (exponential in the depth).

*Please elaborate on it so that anyone can understand.