## CS1674: Homework 11 - Written

**Due:** 12/5/2016, 11:59pm

This assignment is worth 15 points.

- Say a vision system predicts the following scores for a cat image: 10 for the category "cat," 5 for the category "dog," and 3 for the category "cow." Another system predicts scores 8, 6 and 1 for the same categories. Is the softmax loss the same or different for these two systems? (You do
*not* need to show calculations.)
- Briefly, how does gradient descent work?
- What is mini-batch?
- How can we prevent overfitting in a neural network?
- What do lower vs higher convolutional layers in a convolutional neural network capture?
- Why is it
*not* necessary to have a massive amount of data to use convolutional neural networks?