IKT466 Introduction to Machine Learning (Autumn 2025)

By the end of the course the student will be able to:

• Understand and apply fundamental concepts in machine learning and deep learning.
• Evaluate and compare different classification and regression models.
• Implement and optimize machine learning algorithms using Python and relevant libraries.
• Analyze the strengths and weaknesses of different machine learning techniques.
• Develop and fine-tune deep learning models for various applications.
• Apply machine learning and deep learning methods to real-world datasets.

The course provides the students with a deep understanding of machine learning and deep learning principles, covering both theoretical foundations and practical applications. The course is divided into two main parts: classical machine learning models and deep learning techniques. Students will explore various classification and regression models, Bayesian methods, support vector machines, ensemble methods, and deep learning architectures. By the end of the course, students will be able to analyze, implement, and evaluate machine learning and deep learning models using modern frameworks.

Part I: Machine Learning Fundamentals

Key Topics: Linear models, decision theory, kernel methods, and sparse kernel machines.

Additional Models: Bayesian models, SVM, decision trees, random forests, KNN, Naive Bayes, ensemble methods (bagging, boosting, stacking), linear and logistic regression.

Part II: Deep Learning Techniques

Core Concepts: Machine learning basics, feedforward networks, regularization, optimization, convolutional networks, and sequence modeling.

Practical Aspects: Training methodologies and real-world applications.

The course is organized in combination of lectures, assignments, paper studies, labs, report writing and self-study. The tasks are done individually or in small groups with group supervision.

The workload for the average student is approximately 200 hours.