02460 Advanced Machine Learning

2024/2025

Course information
Avanceret machine learning
English
5
MSc
Offered as a single course
Programme specific course (MSc), Business Analytics
Programme specific course (MSc), Human-Centered Artificial Intelligence
Programme specific course (MSc), Mathematical Modelling and Computation
Technological specialization course (MSc), Business Analytics
Technological specialization course (MSc), Human-Centered Artificial Intelligence
Technological specialization course (MSc), Mathematical Modelling and Computation
Spring F1B (Thurs 13-17)
Campus Lyngby
Lectures with exercises, and periods of project work.
13 weeks
F1B
Written examination and reports
Reports and exam are equally weighted. The contribution of each student must be indicated in the reports.
Written exam: 2 hours
Written works of reference are permitted
7 step scale , external examiner
02450. 02456. 02476. 02477. 02405 , This course is an advanced course in machine learning. Students are expected to have passed most of the machine learning courses offered by DTU Compute before attending this course. At a minimum, students are expected to have passed 02450: Introduction to Machine Learning and Data Mining and 02456: Deep Learning. Students will benefit most from the course if they have also passed 02476: Machine learning operations, 02477: Bayesian machine learning, and 02405 Probability Theory. The course can be followed in parallel with 02477.
Søren Hauberg , Ph. (+45) 4525 3899 , sohau@dtu.dk
Lars Kai Hansen , Lyngby Campus, Building 321, Ph. (+45) 4525 3889 , lkai@dtu.dk
Jes Frellsen , Lyngby Campus, Building 321, Ph. (+45) 4525 3923 , jefr@dtu.dk
Mikkel N. Schmidt , Ph. (+45) 4525 5270 , mnsc@dtu.dk
Morten Mørup , Ph. (+45) 4525 3900 , mmor@dtu.dk
01 Department of Applied Mathematics and Computer Science
At the Studyplanner
Please contact the teacher for information on whether this course gives the student the opportunity to prepare a project that may participate in DTU´s Study Conference on sustainability, climate technology, and the environment (GRØN DYST). More infor http://www.groendyst.dtu.dk/english
General course objectives
To provide knowledge of current research topics in generative modeling, including handling issues of identifiability and non-trivial data such as graphs.
Learning objectives
A student who has met the objectives of the course will be able to:
  • Explain in detail how deep generative models work.
  • Operationalise and implement deep generative models.
  • Compare and distinguish the modeling choices in different deep generative models.
  • Reason about which aspects of a statistical model yields identifiable outcomes.
  • Operationalize differential geometric representations in latent variable models.
  • Estimate identifiable distributions from observational data expressed in a learned representation.
  • Operationalize and implement graph neural networks.
  • Reason about the foundations of graph neural networks.
Content
The course consists of 3 modules which each consist of 2-3 weeks of lecturing and two weeks of advanced project work. The topics are deep generative models, geometric representations, and graph neural networks. The focus is on the theoretical foundations and mathematical model components.
Course literature
Deep Generative Modeling. Jakub M. Tomczak.

Differential geometry for generative modeling. Søren Hauberg.

Graph Representation Learning. William L. Hamilton.
Remarks
This course is an advanced course in machine learning and part of the focus area Machine Learning and Signal Processing of the Master of Mathematical Modelling and Computing program.
Last updated
02. maj, 2024