You're tasked to build a fully connected network to classify all animals on images taken in a zoo. Here are some examples of images in your dataset: If there are elephants and alligators in the image. the model network should classify the image as containing two classes: "elephant" and "alligator", no matter how many animals from each class there are. What is a good choice for the last activation of your neural network? Why is that? (Sigmoid, Tanh. ReLU. Softmax)