You would like to train a neural network to classify digits. Your network takes as input an image and outputs probabilities for each of the 10 classes, 0-9. The network’s prediction is the class that it assigns the highest probability to. From the following functions, select all that would be suitable loss functions to minimize using gradient descent:

(A) The square of the difference between the correct digit and the digit predicted by your network

(B) The probability of the correct digit under your network

(C) The negative log-probability of the correct digit under your network.