Third-Cycle Courses

Faculty of Engineering | Lund University

Details for the Course Syllabus for Course EIT195F valid from Spring 2021

Printable view

  • English
  • If sufficient demand
  • The course aim is to provide a broad foundation for machine learning theory as well as state-of-the-art machine learning techniques, e.g., deep neural networks.
  • Introduction and Foundation,

    Linear Models,

    Deep Neural Networks.
Knowledge and Understanding
  • For a passing grade the doctoral student must
  • be able to understand the theory of machine learning and the philosophy behind it, as well as the fundamental ideas behind the state-of-the-art machine learning techniques;
    be able to analyze and identify the main machine learning principles and clearly present the main ideas within the machine learning and artificial intelligence domains;
    be able to analyze, evaluate, and apply state-of-the-art techniques in the machine learning and artificial intelligence domains.

Competences and Skills
  • For a passing grade the doctoral student must
  • be able to carry out a group project investigating and applying state-of-the-art techniques;
    be able to critically read, evaluate and present scientific literature and course material.
Judgement and Approach
  • For a passing grade the doctoral student must
Types of Instruction
  • Seminars
  • Project
Examination Formats
  • Oral exam
  • Seminars given by participants
  • Failed, pass
Admission Requirements
Assumed Prior Knowledge
  • Basics of Probability Theory and Statistics, Basics of Linear Algebra and Numerical Methods, Basics of Algorithms and Data Structures, Programming
Selection Criteria
  • Murphy, Kevin P.: Probabilistic Machine Learning: An introduction. MIT Press, 2021.
Further Information
  • Course coordinator: Amir Aminifar, E-mail:
Course code
  • EIT195F
Administrative Information
  • 2021-04-29
  • Professor Thomas Johansson

All Published Course Occasions for the Course Syllabus

No matching course occasions were found.

0 course occasions.

Printable view