Welcome on the permanent Canvas-site for EDAN96, Applied Machine Learning.

This course used to have the course code EDAN95, and the graduate version still goes as EDAN95F.

Next course occasion:

The course is given the second study period during fall, HT LP 2. For tentative registration deadline and dates (anmälan), see the LTH student web: https://www.student.lth.se/kurs-och-programinformation/kursanmaelan-och-registrering/kursanmaelan/.

General information

Formal course description: 

EDAN96 (Swedish) and EDAN96 (English). This course is also given as EDAN95F to PhD students, see the information for PhD students below.

Course responsible:

Maj Stenmark, maj.stenmark@cs.lth.se

Lectures:

The lectures and lab sessions will be held on campus, it is not possible to take the course remotely.

Course material:

Every course instance has a separate Canvas page, you will be added when you register for the course in Ladok, the registration usually open one week before the study period starts. 

Language:

The course is taught in English (the course responsible, the lecturers and some of the TAs speak Swedish).

Admission:

Prerequisites: 120 credits (hp) in the engineering program or equivalent previous education and 15 credits programming, for example the first and second programming course.

The course will admit a limited number of students (formally 100, but usually up to 160). In case we can not admit all students who fulfills the prerequisites, students will be ranked by number of credits within their engineering program (from high to low).

Re-registration:

If you want to re-register (omregistrera) to finish pending parts of the course / retake the entire course, contact the administration for the formal registration and the course responsible (Maj Stenmark) personally. You will get a place in the course.

Course Policy:

The department has defined a policy against plagiarism of any kind, in particular in case of the course work. You may find it following these links: Samarbete eller fusk (in Swedish) and Cooperation or Plagiarism (in English).

Textbooks:

• Kevin P. Murphy: Machine Learning, A Probabilistic Perspective. MIT Press, 2012, ISBN: 9780262018029. 
• C. M. Bishop: Pattern Recognition and Machine Learning. Information Science and Statistics. New York: Springer, 2006. 
• Andreas Lindholm, Niklas Wahlström, Fredrik Lindsten, Thomas B. Schön: Machine Learning - A First Course for Engineers and Scientists. Cambridge University Press, 2022, https://smlbook.org/book/sml-book-draft-latest.pdf 
• Books not listed in course plan, but mostly easily accessible:
  • Ian Goodfellow Yoshua Bengio Aaron Courville: Deep Learning. MIT Press, 2017. https://www.deeplearningbook.org/ 
    • Aurélien Géron: Hands-On Machine Learning with Scikit-Learn and TensorFlow, Concepts, Tools, and Techniques to Build Intelligent Systems. O'Reilly Media, 2017, ISBN: 9781491962299.
    • Tom Mitchell: Machine Learning. McGraw Hill, 1997, ISBN: 0070428077.

Exchange students:

The office for incoming exchange students handles the registration and course admission for exchange students. The prerequisites are checked a few months before the course registration and exchange students are admitted a few weeks before the course starts. Contact the office for incoming exchange students for deadlines.

PhD students:

Course info for PhD students are found here: https://www.phd.lth.se/english/courses/

To register as a PhD student, send an email to the course responsible in September (approx 2 months before the course starts). PhD students have the same prerequisites as regular students but you also need your supervisor's approval.

For PhD students, the grade is pass/fail and no partial course credits are awarded. You will have your own lab sessions that can run outside of the regular study periods.