Applied Machine Learning
Tillämpad maskininlärning

EDAN96, 7.5 credits, A (Second Cycle)

Valid for: 2026/27
Faculty: Faculty of Engineering LTH
Decided by: PLED C/D
Date of Decision: 2026-04-16
Effective: 2026-05-18

General Information

Depth of study relative to the degree requirements: Second cycle, in-depth level of the course cannot be classified
Elective for: C4-pvs, C4-pvt, D4-bg, D4-mai, D4-se, D4-pv, E4-bg, E4-mi, F4, F4-pv, F4-fm, I4-pvs, MSOC2, N4, Pi4-fm, Pi4-pv
Language of instruction: The course will be given in English

Aim

To give an introduction to fundamental methods and algorithms within Machine Learning and to give an introduction into a selection of specific subdomains and applications. To convey knowledge about breadth and depth of the domain.

Learning outcomes

Knowledge and understanding
For a passing grade the student must

• Understand fundamental machine learning models, their mathematical foundations, basic algorithms, data processing techniques, as well as training and evaluation methods.
• Implement machine learning models, process data, and interpret, evaluate, and improve them during laboratory sessions.
• Be familiar with general models and architectures used in common applications.

Competences and skills
For a passing grade the student must

• evaluate and prepare the necessary data.
• select, implement, and train a model.
• evaluate the results and fine-tune the model.

Judgement and approach
For a passing grade the student must

• be able to assess the applicability of a machine learning method to a given problem,
• understand the limitations of machine learning methods and approaches.

Contents

Fundamental topics in machine learning:

• Unsupervised and supervised learning, classification and regression
• Mathematical foundations: information theory, probability, and statistics
• Likelihood, maximum likelihood, and maximum a posteriori estimation
• Model selection, cross-validation, and evaluation methods
• Decision trees and forests, ensemble methods
• Bayesian classification
• Principal Component Analysis (PCA) and dimensionality reduction
• Linear regression
• Logistic regression
• Neural networks: data preparation, backpropagation, gradient descent, and activation functions
• Convolutional neural networks

Applied topics (overview) include:

• Specific neural network architectures for image analysis.

Examination details

Grading scale: TH - (U, 3, 4, 5) - (Fail, Three, Four, Five)
Assessment:

(Laboratory) Assignments and written exam. To qualify for the exam students must have completed the assignments. The final grade of the course is based on the result of the written examination.

The examiner, in consultation with Disability Support Services, may deviate from the regular form of examination in order to provide a permanently disabled student with a form of examination equivalent to that of a student without a disability.

Modules
Code: 0124. Name: Compulsory Course Items.
Credits: 5.0. Grading scale: UG - (U, G). Assessment: To qualify for a passing grade (3) the laboratory work and assignments must be completed. To take the exam it is necessary to pass all assignments. The module includes: Laboratory work and assignments (passing all assignments is required for passing the course). Further information: Details regarding the compulsory assignments will be found in the course program (syllabus) at the course web site.
Code: 0224. Name: Exam.
Credits: 2.5. Grading scale: TH - (U, 3, 4, 5). Assessment: To qualify for the exam the assignments must be completed. The final grade of the course is based on the result of the written examination. The module includes: Written exam.

Admission

Admission requirements:

• At least 120 credits(hp) in the engineering programme or equivalent previous education.
• (EDA011 Programming, First Course or EDA016 Programming, First Course or EDA017 Programming, First Course or EDA501 Programming, First Course or EDAA20 Programming and Databases or EDAA45 Introduction to Programming or EDAA50 Programming, First Course or EDAA55 Programming, First Course or EDAA65 Programming, First Course or EDAA70 Introduction to Programming Using Python or EDAA80 Introduction to Programming or EDAA85 Introduction to Programming or EDAA90 Introduction to Programming and Databases or EDAB05 Introduction to Programming)
    and
  (EDAA01 Programming - Second Course or EDAA30 Programming in Java - Second Course or FMNN25 Advanced Course in Numerical Algorithms with Python/SciPy or FRTF25 Introduction to Machine Learning, Systems and Control)

Reading list

• Kevin P. Murphy: Machine Learning - A Probabilistic Perspective. MIT Press, 2012, ISBN: 9780262018029. Reference text about machine learning.
• C. M. Bishop: Pattern Recognition and Machine Learning - Information Science and Statistics. Springer, New York, 2006, ISBN: 9780387310732. Reference text about machine learning.
• A. Lindholm, N. Wahlström, F. Lindsten, T.B. Schön: Machine Learning - A First Course for Engineers and Scientists. Cambridge University Press, 2022, ISBN: 978-1-108-84360-7. Introductory textbook.

Contact

Course coordinator: Maj Stenmark, maj.stenmark@cs.lth.se
Teacher: Pierre Nugues, pierre.nugues@cs.lth.se
Examinator: Maj Stenmark, maj.stenmark@cs.lth.se
Course homepage: https://cs.lth.se/edan96/

Further information