Machine Learning Course | 8-Week Postgraduate Program | KTH Royal Institute of Technology
Course Details
| Exam Registration | 3912 |
|---|---|
| Course Status | Ongoing |
| Course Type | Elective |
| Language | English |
| Duration | 8 weeks |
| Categories | Computer Science and Engineering, Robotics |
| Credit Points | 2 |
| Level | Postgraduate |
| Start Date | 19 Jan 2026 |
| End Date | 13 Mar 2026 |
| Enrollment Ends | 02 Feb 2026 |
| Exam Registration Ends | 16 Feb 2026 |
| Exam Date | 28 Mar 2026 IST |
| NCrF Level | 4.5 — 8.0 |
Master the Future: An In-Depth Postgraduate Course in Machine Learning
In today's data-driven world, Machine Learning (ML) stands as a cornerstone of modern innovation. From powering autonomous vehicles and intelligent assistants to optimizing complex industrial processes, the ability to develop algorithms that learn from data is a transformative skill. This 8-week postgraduate course, offered by the prestigious KTH Royal Institute of Technology in Stockholm, provides a rigorous and comprehensive foundation in this critical sub-discipline of Artificial Intelligence (AI).
Course Overview: A Deep Dive into AI's Core
This course is meticulously designed to place machine learning within the broader context of AI while delivering hands-on knowledge of its most powerful techniques. Over eight intensive weeks, you will move from foundational concepts to advanced applications, guided by world-class faculty. The curriculum is ideal for professionals and postgraduate students aiming to build or solidify their expertise in adaptive systems and data pattern recognition.
Learn from Leading KTH Experts
Your instruction will be led by a distinguished team of professors from KTH's School of Electrical Engineering and Computer Science, ensuring you learn from researchers at the forefront of the field.
- Prof. Carl Gustaf Jansson: Tenured Professor in Artificial Intelligence. His research in Knowledge Representation and Machine Learning, with a focus on intelligent interfaces, provides a strong theoretical foundation for the course.
- Prof. Henrik Boström: Tenured Professor in computer and data science. A specialist in ensemble learning and interpretable models (like decision trees and rules), he brings crucial insights into making ML models understandable and reliable.
- Assoc. Prof. Fredrik Kilander: Associate Professor with a PhD in Machine Learning, specializing in Conceptual Clustering. His broad teaching experience and research in ubiquitous computing connect ML theory to real-world, pervasive applications.
Who Should Enroll?
This course is crafted for a dedicated audience ready to engage with advanced material.
- Intended Audience: Postgraduate students, software engineers, data analysts, researchers, and any professional with a serious interest in mastering machine learning principles.
- Prerequisites: A solid grounding in basic computer science and applied mathematics is required to fully engage with the algorithmic and mathematical concepts presented.
- Industry Support & Relevance: The skills taught are in high demand across numerous sectors. This course directly supports careers in autonomous vehicle development, robotics, intelligent software assistants, financial technology, healthcare analytics, and general data mining.
Your 8-Week Learning Journey
The course layout is structured to build knowledge progressively, ensuring a logical and thorough understanding of machine learning.
| Week | Focus Area | Key Topics |
|---|---|---|
| Week 1 | Introduction | Course overview, history, and the role of ML in AI. |
| Week 2 | Problem Characterization | Defining learning tasks, supervised vs. unsupervised learning, problem formulation. |
| Week 3 | Forms of Representation | How data and knowledge are structured for learning algorithms. |
| Week 4 | Symbolic Inductive Learning | Decision tree learning, rule-based systems, learning with weak theories. |
| Week 5 | Theory-Guided Learning | Inductive Logic Programming (ILP), leveraging prior knowledge. |
| Week 6 | Neural Network Approaches | Introduction to Artificial Neural Networks and Deep Learning. |
| Week 7 | Tools & Influences | Practical software/resources and insights from Cognitive Science. |
| Week 8 | Synthesis & Application | Case studies, demonstrations, and preparation for final assessment. |
Course Materials and Outcomes
Participants will receive comprehensive course notes and presentation materials. While these form the core content, optional textbook readings will be suggested for students wishing to delve deeper into specific areas of machine learning theory.
By completing this course, you will gain a robust, practical understanding of core ML paradigms. You will be equipped to:
- Understand and characterize different machine learning problems.
- Implement and evaluate algorithms like decision trees for inductive learning.
- Comprehend the principles behind neural networks and deep learning.
- Appreciate the role of reinforcement learning and theory-guided approaches.
- Apply this knowledge to real-world problems in computing, engineering, and robotics.
Take the next step in your technical career. Join this intensive postgraduate journey into Machine Learning and build the expertise to develop the intelligent systems of tomorrow.
Enroll Now →