ETC3250: Tutorial 7 Help Sheet

Exercises

Question 1

Hint 1: Where to go for details on the data

Before doing an analysis you should always get a good idea of the data you are working with. There are some details on the data set here and you can also call ?dataset_fashion_mnist to get some details.

Question 2

Hint 1: Where to go for information

There are several functions for checking the details of a data set, they include dim, glimpse, head, summarise, etc. To plot the images, you can just use ggplot. The images are 28x28 pixel

Hint 2: Why this is important

It is important to know what your data looks like after every transformation too. That way you understand the input and output of every function. After running those code fashion_mnist$train is a list that contrains two datasets, x and y. fashion_mnist$train$x is an 60000 x 28 x 28 dimension array. That means

Question 4

Hint 1: Where to go for layer information

Check lecture 6 slide 5-6 for a simple neural network structure, and check lecture 6 slide 11-12 for a look at how this structure fits into the model process

Hint 2: Extra hint

Your final layer is related to what you are trying to predict, and your hidden layers are related to model flexibility.

Hint 3: Where to go for loss and optimiser information

Read the help sheet for the compile function to understand these parameters. ?keras::compile.keras.engine.training.Model should take you there (there are a lot of functions called compile so using the full name is easier). Lecture 6 slide 11-12 also have some information related to this question. You can also

Question 6

Hint 1: Why you might get a different result

Typically if you get a different result to someone else despite running identical code on an identical data set, it means the function uses randomness somewhere in the function. Think about where a neural network might use randomness and think about what function could be used to prevent this from happening.

Question 7

Hint 1: How to read

This code will provide you with a confusion matrix. If a particular class if frequently predicted as another class, this will appear in the confusion matrix as a large number off the diagonal.

Question 9

Hint 1: Re-explain question

By “Explain how the class structure matches any clustering” Di means you should explain if the classes are visibly separated in the PCA and UMAP plots.

If one of these methods can separate the classes and another cannot, what does that say about our method and/or input?

Hint 2: Interpreting the 9D Simplex

Lecture 6 slide 55 has an example of a simple case where you need to interpret a 3D simplex (three classes). This question requires