Based on a previous version by Michael Gutmann.
Timetable
Semester week | Date (place) | Activity | Date (place) | Activity |
wk1 | Thu 17/01 (ALT) | lecture 1 | ||
wk2 | Wed 23/01 (AT-6.06) | lab 1 | Thu 24/01 (ALT) | lecture 2 |
wk3 | Wed 30/01 (AT-6.06) | lab 2 | Thu 31/01 (LG34) | lecture 3 |
wk4 | Wed 06/02 (AT-6.06) | lab 3 | Thu 07/02 (LTC) | lecture 4 |
wk5 | Wed 13/02 (AT-6.06) | lab 4 | Thu 14/02 (LTC) | lecture 5 |
wk6 | ||||
wk7 | Wed 06/03 (AT-6.06) | poster session | Thu 07/03 (F.21) | poster session |
wk8 | Wed 13/03 (AT-6.06) | poster session | ||
wk9 | Wed 20/03 (AT-6.06) | poster session | Thu 21/03 (F.21) | poster session |
wk10 | ||||
wk11 | Thu 04/04 (LTC) | Recap, Q&A |
Important dates
Deadline for your paper preference | Fri 8 Feb 2019, 4pm |
Deadline for your project info | Fri 15 Feb 2019, 4pm |
Poster PDF deadline | Mon 25 February 2019, 9am |
Mini-project interim report deadline | Tue 12 March 2019, 4pm |
Mini-project final report deadline | Fri 5 April 2019, 4pm |
Exam | Exam diets |
Labs (weeks 2-5), poster sessions (weeks 7-9):
Wednesdays:
09:00 - 10:50 (group 1), 11:10 - 13:00 (group 2)
Appleton Tower, room 6.06
Lectures (weeks 1-5, 11), poster sessions (weeks 7, 9):
Thursdays:
15:10 - 17:00
Medical School, Room 425 Anatomy Lecture Theatre (weeks 1, 2)
Patersons Land, LG34 (week 3)
David Hume Tower, Lecture Theatre C (weeks 4, 5, 11)
7 George Square, F.21 (weeks 7, 9)
Lectures
The lecture is accompanied by lecture notes (they will be updated as we progress).
- Lecture 1
Introduction to the data analysis process, simple descriptions and preprocessing of data
opening slides - Lecture 2
Principal component analysis
- Lecture 3
Probabilistic PCA, dimensionality reduction by PCA - Lecture 4
Dimensionality reduction by kernel PCA, multidimensional scaling, isomap - Lecture 5
Evaluating the performance in predictive modelling (e.g. classification and regression), techniques for choosing hyper-parameters
Computer labs
The course has four computer labs on topics introduced in the lecture. The labs will allow you to play with different methods to gain some intuitive understanding and provide you with practical tools for the mini-project. There is a GitHub repository for the labs.
- Lab 1 on simple data descriptions and preprocessing
- Lab 2 on principal component analysis
- Lab 3 on dimensionality reduction
- Lab 4 on performance evaluation and hyperparameter/model selection
Poster presentations
In the second half of the course, we will have poster presentations on some of the papers listed on the papers page. Feel free to propose papers yourself but please check with the lecturer about suitability.
Detailed instructions and information on the format of the presentations can be found on the papers page.
Mini-projects
The goal of the project is to apply data mining methods to a real dataset. We have a list of potential datasets (same as for the IRDS course). For each dataset, the web page gives a description of the task to be undertaken. You will produce a project report that will be assessed.
Please have a look at the mini-projects page for detailed instructions and information on the format of the report.