MLPR 2021 activities timeline
As soon as possible, work through the background section of the notes. The administration page explains how the course is assessed and how the activities work.
Links to question sheets and activities will appear throughout the Semester. The precise course content may change. You may need to refresh the page.
Weekly checklist:
- Online class meeting (4:10–5pm Mondays, weeks 1–10), Zoom or recording.
- Weeks 3–9: submit core tutorial questions by 2pm Monday, attend your in‑person group. (See administration page for details.)
- Work through the week’s notes, including videos and questions (not assessed).
- Weeks 2–8: prepare for next week’s tutorial.
- Weeks 3–9: assignment work as appropriate.
Week 1: 20 September –
- First class meeting: Monday 20 September, 16:10-17:00, (Zoom or recording).
- Sign up for the class Forum (hypothesis).
- w1 notes: Introduction to ML with Linear Regression
- Work through any remaining background material.
Week 2: 27 September –
- Class meeting: Monday 16:10-17:00, (Zoom or recording).
- w2 notes: ML fundamentals: generalization, error bars, Gaussians
- Reminder: studying the notes includes doing the questions; don't fall behind from the start!
- Prepare for Tutorial 1 next week. (Tutorial administration information.)
Week 3: 4 October –
- Tutorial 1 – submit core questions by 2pm Monday (4 Oct).
- Class meeting: Monday 16:10-17:00, (Zoom or recording).
- w3 notes: Classification and gradient-based fitting
- Tell us your assignment 1 pair preference. First allocation of pairs at 9:30am Tuesday (5 Oct). We need your pair (or no pair) preference before you can enter answers. Please be patient while we process these.
- Start work on Assignment 1 (print). You can do it by yourself or in a pair.
- Prepare for Tutorial 2 next week.
Week 4: 11 October –
- Tutorial 2 – submit core questions by 2pm Monday (11 Oct).
- Class meeting: Monday 16:10-17:00, (Zoom or recording).
- w4 notes: Bayesian linear regression
- Prepare for Tutorial 3 next week.
- Finish Assignment 1 (print).
Week 5: 18 October –
- Tutorial 3 – submit core questions by 2pm Monday (18 Oct).
- Class meeting: Monday 16:10-17:00, (Zoom or recording).
- Assignment 1 due Tuesday 19 October, 2pm. (0% of final mark)
Feedback is only guaranteed for submissions made on time. - w5 notes: Bayesian model choice and Gaussian processes
- Prepare for Tutorial 4 next week.
Week 6: 25 October –
- Tutorial 4 – submit core questions by 2pm Monday (25 Oct).
- Class meeting: Monday 16:10-17:00, (Zoom or recording).
- w6 notes: More detailed models: Gaussian process kernels, more non-Gaussian regression
- Prepare for Tutorial 5 next week.
- Look at Assignment 2 (print) and schedule when you'll do it in weeks 6–9. You can do it by yourself or in a pair.
- Tell us your assignment 2 pair preference by 2pm Monday (25 Oct).
Week 7: 1 November –
- Tutorial 5 – submit core questions by 2pm Monday (1 Nov).
- Class meeting: Monday 16:10-17:00, (Zoom or recording).
- w7 notes: Neural Networks
- Prepare for Tutorial 6 next week.
Week 8: 8 November –
- Tutorial 6 – submit core questions by 2pm Monday (8 Nov).
- Class meeting: Monday 16:10-17:00, (Zoom or recording).
- w8 notes: Autoencoders, PCA, Netflix Prize
- We hope you haven't forgotten Assignment 2 (print).
- Prepare for the final Tutorial 7 next week.
Week 9: 15 November –
- Tutorial 7 (last one) – submit core questions by 2pm Monday (15 Nov).
- Class meeting: Monday 16:10-17:00, (Zoom or recording).
- w9 notes: Bayesian logistic regression, Laplace approximation
- Finish Assignment 2 (print), if you haven't already.
Week 10: 22 November –
- Assignment 2 due Monday 22 November, 2pm. (25% of final mark)
Late work and extensions subject to Rule 1 of the School Late Policy. - Class meeting: Monday 16:10-17:00, (Zoom or recording).
- w10 notes: Sampling-based approximate Bayesian inference, variational inference
- (No tutorial)
- Please fill out the course survey by 5 December.
- Take a few days off! Then revise for the exam.
December Exam (65% of your final mark)
- The date and time of the December 2021 exam is available on the Exam timetable (deep link:search for MLPR's course code INFR11130 on this form).
- The exam will be online, and open book. You must complete it within the scheduled 2 hour time window. The exam has been written with this time limit and the online format in mind. You must not communicate with others during that time, or about the exam later the same day (in case someone has extra time due to a learning adjustment, which they may not wish to disclose to you).
- You will access the exam via the "Exam" link in the sidebar of the course Learn page.
- A question could ask you to write a short piece of Python code (e.g., one or two lines), which you should be able to run.
- The library has past exam papers. Although you may not be able to do every question: the course has changed slowly over the years, after a big change in 2016. There is no past paper from 2020.