DTSC301 Applied Machine Learning
Assignment 1
Weighting: 20%
Due Date: 5pm, Friday 16th June (end of Week 5)
Submit your report and Jupyter Notebook (as .ipynb) or Spyder code file (as .py) via iLearn.
Overview
Your task is to use what you have learned in the first 3 lectures and workshops to predict which
category newsgroup text belongs to.
I have uploaded a template notebook which contains the simplest possible solution, which you can use
as a starting point. Your goal is to build the best model you can. Remember a good model sits right at
the border between underfitting and overfitting – it maximizes accuracy while minimizing the
network size.
Report Template
Aim to produce a concise report. There is no need to introduce Deep Learning or the problem etc. in
any great detail.
A good approach is to use each of the 7 steps in the "Universal workflow of machine learning" as
guidance for sections / headings in your document. Naturally, you would also add a presentable title
page, exec summary, and conclusion.
Focus on explaining why you made the decisions and choices you made. I can see what you did in the
notebook code you upload… what I want to know is why you made those choices.
Marking thoughts
• I value conciseness and elegance in coding.
• I value your explanations as to why you made the choices you made.
• I value the quality of the model – higher test accuracy and a lower number of network
parameters makes a better model. Achieving this takes considerable effort and thought, which
will be rewarded.
o Ensure you show your test accuracy and call model.summary() on your final model