SF2935 HT20-1 Modern Methods of Statistical Learning

SF2935 HT20-1 Modern Methods of Statistical Learning

SF2935 Modern methods of statistical learning

Lecturer & examiner: Pierre Nyquist.

Office: 3539 (5th floor). Email: pierren@kth.se. Phone: 08-790 7311

Teaching assistant: TBA

Information related to Covid-19:

Due to the on-going pandemic KTH has imposed strict regulations on how courses are taught during the fall semester 2020. As a result this course will be given online, with no campus activities. Course activities will take place during the assigned time slots (see the schedule) and the exact form of these activities will be outlined at the start of the course; see below for some information about the different activities (weekly quizzes, final exam etc.).

Course description: 

This course gives an introduction to standard methods for statistical learning and the mathematical principles underpinning these methods. The purpose is to provide students with a broad introduction to common methods for supervised and unsupervised learning and the mathematical tools used to design and analyse such methods. The course combines theory, emphasising the mathematical nature and the theory underlying statistical learning,  and computational experiments to give an understanding for the building blocks of various machine learning methods now being used in all aspects of society.

The following is a rough list of the general topics that will be discussed in the course: Introduction to statistical learning, PAC-learning, half-spaces and perceptrons, regression, artificial neural networks, Bayesian stat & learning, linear methods for supervised classification, tree-based methods, support vector machines, principal component analysis, random forests unsupervised learning, probability in high dimension.

Up-to-date information about what has been covered in lectures, updates on projects etc. can be found under "Current information".

Course literature: The course is based on a number of sources that will be summarised in lecture notes posted on Canvas. For an overview of the topic, omitting the more technical details, the course book previously used is a good source: G. James, D. Witten, T. Hastie, R. Tibshirani An introduction to Statistical Learning. We will announce specific sources for the different parts of the course as we go along for students who are interested in going beyond the lecture notes. More advanced references will also be provided for interested students - these are by no means required reading.

Intended learning outcomes: For the methods presented in the course, the student shall possess both theoretical and practical understanding of how the methods work, which ones to choose for a given problem and how to implement rudimentary versions of them. Computer-aided projects form an essential learning activity.

To pass the course the student shall be able to

    • formulate and apply methods for supervised learning,
    • formulate and apply methods for unsupervised learning,
    • apply mathematical theory to analysis and explain properties of methods in statistical learning,
    • design and implement methods in statistical learning for different tasks.

Examination: The course has mandatory project work (hand-in assignments) and a final written exam. The projects account for 3.0 ECTS (graded P/F) and the written exam for the remaining 4.5 ECTS.  More information about the projects will be available shortly after the start of the course. 

Due to the course being given online this semester, the final exam will be on the form of a take-home exam on October 21, 08:00-13:00. The exact form of the exam will be described in the syllabus at the start of the course. Grades are given in the range A-F or Fx, where Fx gives the right to a complementary examination to potentially reach the grade E. Registration using MyPages is required for the exam. Please refer to Studentexpeditionen Matematik / Student Office Mathematics for any questions regarding enrolment in the course and admission for the exam.

There will be (almost) weekly quizzes in Canvas that can generate up to 5 bonus points for the final exam. Each quiz will focus on the topics of the corresponding weeks and participation is voluntary; more information will be provided at the start of the course.

Support for students with disabilities

Students with disabilities may have the right to certain compensatory support, for example during examination.  KTH has coordinators for students with disabilities, Funka (Länkar till en externa sida.) , who deal with issues relating to functional disabilities. Please contact Funka at funka@kth.se for information about the support they can offer.