Machine Learning (2026)
Doctoral School of Engineering and Science at Aalborg University
Welcome to Machine Learning (2026)
Description: Machine learning revolves around creating computer programs that enable machines to learn from examples or experiences. It's an interdisciplinary field at the intersection of computer science, engineering, statistics, and pattern recognition. In recent decades, it has witnessed rapid theoretical progress and extensive real-world applications across various domains. These applications encompass machine perception (like speech recognition and computer vision), natural language processing (including large language models), time-series prediction, sciences, recommendation systems, medical diagnosis and prognosis, autonomous vehicles, predictive maintenance, sentiment analysis, and beyond. Machine learning serves as a driving force behind the ongoing wave of artificial intelligence.
This course offers a comprehensive introduction to machine learning, with the goal of elucidating fundamental methods and their theoretical underpinnings, while also addressing practical machine learning problems such as pattern recognition, prediction, clustering, and generative modeling.
Topics will include:
- Supervised learning methods: logistic regression, support vector machines, neural networks, K-nearest neighbors, and decision trees
- Unsupervised learning and clustering methods: K-means, Gaussian mixture models, Expectation Maximization algorithm, and principal component analysis
- Deep learning methods: deep neural networks, long short-term memory recurrent neural networks, convolutional neural networks, generative adversarial networks, and Transformers.
- Probabilistic graphical models - Reinforcement learning
For additional information, updates, and registration, please refer to AAU PhD Moodle via the link provided on the right side of this page.