Course content

This course introduces fundamental principles and practical methods in machine learning and deep learning. Topics include:

• Core concepts in supervised and unsupervised machine learning
• Data quality, preprocessing, and evaluation metrics
• Classical machine learning methods and their strengths and limitations
• Neural network architectures, including CNNs and Transformers
• Model evaluation, optimisation, robustness, and interpretability
• Applications of machine learning in areas such as computer vision and medical imaging

Learning outcome

Knowledge

The candidate:

• can explain fundamental concepts and types of Machine Learning and deep learning approaches.
• can understand the quality of data and evaluation metrics.
• can understand strengths and limitations of classical ML methods.
• can describe and implement basic Neural Network architectures, including CNNs and Transformers.
• can understand black-box nature of modern ML algorithms and develop methods to mitigate them.

Skill

The candidate:

• can use libraries for machine learning, including Scikit-learn, Keras, and TensorFlow
• can preprocess data, build pipelines, and implement structured and well-documented ML workflows.
• can implement key ML algorithms including linear models, SVMs, decision trees, ensembles, and neural networks.
• can evaluate and optimize models and analyze the performance to ensure robustness and reliability.

General competence

The candidate:

• can explain and make use of knowledge for solving problems in application scenarios like computer vision, medical imaging and across different topics.
• can analyze ML algorithms and their applications in critical and reflective manner.

Learning methods and activities

The course will be offered with lectures and practical assignments, including exercises and small projects. Some sessions may involve group discussions or guest lectures on related research topics.​

Specific conditions

Recommended previous knowledge

Basic programming skills, linear algebra (matrix and vector operations) and calculus.​

Required previous knowledge

None

Course materials

Text books and supplementary reading materials will be provided at the start of the semester.