$$\notag $$

Week 8, 9–13 November

Welcome to week 8! This week we introduce Neural Networks.

The main goal of this week is to understand the idea behind neural networks: defining deeper non-linear functions, and learning/fitting all of their parameters using gradient based methods.

The first note (w8a) is important for thinking about the functions that you can easily represent. Please answer the short initial question in w8a, and then look at the answer, before your discussion group meets. The popular neural network architectures and design choices change. You can skip w8b at first, if short on time. If you want to use neural networks in the future, you will have to experiment (using training, validation, and test sets) and do more reading.

The class test is on Monday this week. See below.

Your mark for other work this week comes from: completing the discussion task (10%), attempting the in-note questions (20%), and this week’s assessed questions (70%). Full details on the assessments page including rules you must know.

Office hours:

You can meet us on MS Teams in the Meet-up channel of the MLPR 2020/21 Chat team on Friday at 9:30 AM and 4:30 PM UK time (GMT). One of Arno or Iain will be there. If you want to discuss something individually, please contact us by email: Arno or Iain .

Here is what you need to do in Week 8:

We recommend that you aim to finish the questions (in the notes and question sheet) and submit your discussion report by the end of Thursday. We will assess only what you have submitted by 4pm UK time on Friday.

As in the Informatics late policy, extensions are not available for weekly hand-ins. We expect many students to miss or under-perform on one hand-in, and will discount the one with the lowest mark. If you experience more significant disruption to your studies, you may need to file special circumstances. Consult your Personal Tutor or Student Support team. Lecturers on a course cannot make allowances outside these procedures.