Description
Course syllabus
Goals. You get introduced to the theory of statistical models (uniform random graphs, stochastic block models, graphons) used in predicting and learning structural properties of networks based on incomplete and noisy observations. The course is targeted to students in mathematics, operations research, and computer science.
Schedule. The course starts with the first lecture on Mon 9 Sep 2019, and there will be five weeks of lectures and exercises during Sep–Oct. The course ends on Thu 17 Oct 2019 with an afternoon workshop where the project works of the course are presented.
- Lectures: Mon 12–14 @ Room M237 (Otakaari 1) and Thu 12–14 @ Room M3 (Otakaari 1)
- Exercises: Thu 14–16 @ Room Y307 (Otakaari 1)
Extent. The extent of the course is 5 ECTS credits, which amounts to roughly 130 h of work by the student.
Grading and evaluation. There is no exam. Instead, the grade of the course is determined by written homework solutions and a project work. The course grade is primarily determined by the homework solutions, so that solving (40+10*k) percent of the homework problems with detailed solutions is sufficient to obtain a grade k. The project work is graded as fail/good/excellent. The project work must completed to pass the course. An excellent project work increases a course grade 0 < k < 5 up by one.
Prerequisites: There are no formal prerequisites but some background in probability and statistics is highly recommended, for example MS-C2111 Stochastic processes and MS-C1620 Statistical inference.
Lecturer: Prof. Lasse Leskelä
Teaching assistant: MSc Joona Karjalainen
- Lectures: Mon 12–14 @ Room M237 (Otakaari 1) and Thu 12–14 @ Room M3 (Otakaari 1)