MLPR 2024 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:

• In-person lectures (recordings made available) (9am–9:50am Tue/Wed/Thu, weeks 1–10).
• Weeks 1–10: Lectures: 9am–9:50am Tue/Wed/Thu:
  • Tuesday: Teviot Lecture Theatre - Doorway 5 - Medical School, Teviot.
  • Wed/Thu: G.07 Meadows Lecture Theatre - Doorway 4 - Medical School, Teviot.
  • Lecture Recordings (within 24 hours, need class registration).
• Weeks 1–10: study the notes, including in-note questions (not assessed).
• Weeks 2–8: prepare for the next week’s tutorial.
• Weeks 3–9: Tutorials. (See administration page for details.)
• Weeks 3–9: assignment work as appropriate.

Week 1:  16 September –

• First class meeting: Tuesday 17 September, 9am.
• Sign up for the class Forum (hypothesis).
• w1 notes: Introduction to ML with Linear Regression
• Work through any remaining background material.

Week 2:  23 September –

• w2 notes: ML fundamentals: generalization, error bars, Gaussians
• Reminder: studying the notes includes doing the questions; don't fall behind from the start! Check your status.
• Prepare for Tutorial 1 next week. (Tutorial administration information.)

Week 3:  30 September –

• w3 notes: Classification and gradient-based fitting.
• Tutorial 1 questions (for Thu or Fri).
• Tell us your assignment 1 pair preference. First allocation of pairs at 2pm Tuesday (1 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:  7 October –

• w4 notes: Bayesian linear regression
• Tutorial 2 questions (for Thu or Fri).
• Prepare for Tutorial 3 next week.
• Finish Assignment 1 (print).

Week 5:  14 October –

• Assignment 1 due Monday 14 October, 12 noon. (0% of final mark)
  Feedback is only guaranteed for submissions made on time.
• w5 notes: Bayesian model choice and Gaussian processes
• Tutorial 3 questions (for Thu or Fri).
• Prepare for Tutorial 4 next week.

Week 6:  21 October –

• w6 notes: More detailed models: Gaussian process kernels, more non-Gaussian regression
• Tutorial 4 questions (for Thu or Fri).
• 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 (link not working yet) by 2pm Tuesday (22 Oct).

Week 7:  28 October –

• w7 notes: Neural Networks
• Tutorial 5 questions (for Thu or Fri).
• Prepare for Tutorial 6 next week.

Week 8:  4 November –

• w8 notes: Autoencoders, PCA, Netflix Prize
• Tutorial 6 questions (for Thu or Fri).
• We hope you haven't forgotten Assignment 2 (print).
• Prepare for the final Tutorial 7 next week.

Week 9:  11 November –

• w9 notes: Bayesian logistic regression, Laplace approximation
• Tutorial 7 (last one).
• Finish Assignment 2 (print), if you haven't already.

Week 10:  18 November –

• Assignment 2 due Monday 18 November, 12 noon. (25% of final mark)
  Late work and extensions subject to Rule 2 of the School Late Policy.
• w10 notes: Sampling-based approximate Bayesian inference, variational inference
• (No tutorial)
• Please fill out the course survey (link not working yet) by TBD December.
• Take a few days off! Then revise for the exam.

December Exam (75% of your final mark)

• We expect the exam to be between 9–20 December 2024 (source: Semester Dates). The date and time will appear in the Exam timetable as soon as it's been set. We don't have early access to the date.
• We expect the exam to be a closed-book pen-and-paper exam, held in person in Edinburgh. However this is still subject to confirmation by the University.