Questions and answers

1. Can a perceptron and/or a neural network solve the problem of classifying data that is linearly separable?

Yes, both can.

1. Can a perceptron and/or a neural network solve the problem of classifying data that is non-separable? 

Yes, both can. However, the perceptron will go on forever unless we specify a stopping condition such as a maximum number of iterations (updates), or stopping if the number of misclassified points does not decrease after a number of iterations.

1. What are the changes in the ML filed that have enabled us to have deep learning today?

(A) backpropagation algorithms, batch training, ReLUs, and so on;

(B) computing power, GPUs, cloud, and so on.

1. Why is generalization a good thing?

Because deep neural networks are most useful when they can function as expected when they are given data that they have not seen before, that is, data on which they have not been trained.