Statistical Deep Learning

Course  content: This course introduces basic as well as modern concepts of statistical learning in terms of artificial neural networks (deep learning), with applications in statistical data analysis. Topics treated include feedforward networks, regularization and optimization of networks with many layers, convolutional networks, recurrent networks and validation methods. The course may also include some of the following modern topics; autoencoders, representation learning, attention and transformers, information theoretic concepts of deep learning, explainable AI, etc.

Teacher: Chun-Biu Li (cbli@math.su.se)

TA: Nik Tavakolian  (nik.tavakolian@math.su.se)

Course literature: "Deep Learning" by Goodfellow et al., MIT Press, 2016

Course plan: 2022 Edition

Class Schedule

Remarks: The lecture plan below may subject to change (add or skip some topics) during the semester depending on the progress of the class.

Examiner: Chun-Biu Li

Course Exam & Projects: The course consists of the following parts,

Part 1: (Theory 3.5 hp) There will be an open-book written exam on Mar 16, 2026. The exam covers some of the recommended exercises given in all classes. Registration for the exam in Ladok is required to take the exam.

Part 2: (Project 4 hp) 3 small projects - on materials in all lectures will be given as hand-in written assignments. 1 additional small project - two students work as a group pick up a dataset (see "Project 4" below for a list of databases), then analyze using any deep learning method with validations and present the result orally for the class (~20 mins) on Mar 9.

Examination Rules at the Department of Mathematics.

Grading Criteria: See below