Machine Learning

Faculteit Science and Engineering
Jaar 2022/23
Vakcode WMAI010-05
Vaknaam Machine Learning
Niveau(s) master
Voertaal Engels
Periode semester I b

Uitgebreide vaknaam Machine Learning
Leerdoelen At the end of the course, the student is able to:
1) understand and appreciate universal challenges that arise in (almost) every machine learning (ML) project: curse of dimensionality, bias-variance tradeoff, choice of loss function, architecture design (structural bias), and know about standard coping strategies (dimension Reduction, regularization, cross-validation)
2) give a coarse overview of the rich landscape of modern ML (supervised / unsupervised / reinforcement learning,
different modeling attitudes, goals and methods in different subfields of ML)
3) understand basic algorithmic techniques that is sufficient to allow him/her to practically apply these techniques by programming from scratch or using a high-level toolbox
4) easily and quickly implement simple (but not necessarily poorly performing) linear, baseline ML pipelines for supervised learning problems
5) design, implement, run, test and evaluate a more complex, multi-module, nonlinear ML pipeline for supervised learning problems, possibly including unsupervised components
Omschrijving Machine learning (ML) is about algorithms which are fed with (large quantities of) real-world data, and which return a compressed model of the data. An example is a spoken language model: the input data are speech recordings, from which ML methods build a model of spoken English -- useful, for instance, in automated speech recognition systems. There exists a large number of formalisms in which such models can be formulated and implemented, and an even larger diversity of learning algorithms to estimate such models from data. However, there is only a relatively small number of fundamental challenges which are common to all of these formalisms and algorithms. This lecture introduces such fundamental concepts and a choice of standard model formalisms (decision trees, linear classifiers and regressors, K-means clustering, self-organizing feature maps, sampling / energy based distribution modeling, hidden Markov models and graphical models, feedforward and recurrent neural networks).
There will be a practical where students will implement their own machine learning system and they will write a report about this system and the obtained results. Furthermore, there will be a written final exam at the end of the course.
Uren per week
Onderwijsvorm Hoorcollege (LC), Opdracht (ASM), Practisch werk (PRC), Werkcollege (T)
(There will be lectures given by the lecturer and a computer practicum.)
Toetsvorm Meerkeuze toets (MC), Verslag (R)
(Final exam (multiple choice) and semester project report each count 50% toward the course grade. A minimum grade of 5.0 in the final exam is needed to pass the course.)
Vaksoort master
Coördinator Prof. Dr. H. Jaeger
Docent(en) Prof. Dr. H. Jaeger
Verplichte literatuur
Titel Auteur ISBN Prijs
Lecture notes, specific for this course. Open access; online via Nestor Herbert Jaeger
Entreevoorwaarden Mandatory: No prior knowledge is assumed. Please note, however, that the student is expected to have a relevant BSc degree.

Advised: Machine learning is a rather math-heavy sector of AI. A solid knowledge of basic linear algebra is essential in order to do well in this course. Participants should have a clear understanding of concepts like, for instance, eigenvectors, coordinate transformations, linear subspaces and projections, inner products and quadratic forms. A good working knowledge of statistics / probability theory is likewise needed (participants should know the difference between expectation and average). Compared to linear algebra and probability, the background needed from calculus is less demanding – it is enough to know what partial derivatives / gradients are.
Opmerkingen This course is NOT an introduction to deep learning! But it is a highly recommended preparation for the follow-up course Deep Learning (WMAI017-05).
Opgenomen in
Opleiding Jaar Periode Type
MSc Applied Mathematics: Computational Mathematics  (Computational Mathematics: Guided choice) - semester I b keuzegroep
MSc Applied mathematics  (Specialisatie: Statistics and Data Science) - semester I b keuzegroep
MSc Applied mathematics  (Specialisatie: Computational Mathematics) - semester I b keuzegroep
MSc Artificial Intelligence  (A - General Mandatory Course Units) 1 semester I b verplicht
MSc Astronomy: Quantum Universe  (Optional Courses in Data Science (DS)) - semester I b keuze
MSc Behavioural and Cognitive Neurosciences: Behavioural Neurosciences  (Electives: courses from other programmes) 2 semester I b keuze
MSc Behavioural and Cognitive Neurosciences: Cognitive Neuroscience & Modelling  (Electives: courses from other programmes) 2 semester I b keuze
MSc Behavioural and Cognitive Neurosciences: Molecular & Clinical Neurosciences  (Electives: courses from other programmes) 2 semester I b keuze
MSc Computational Cognitive Science  (C - Elective Course Units) - semester I b keuze
MSc Computational Cognitive Science  (B - Mandatory Course Units Computational Cognitive Neuroscience) 1 semester I b verplicht CCN
MSc Computing Science: Data Science and Systems Complexity  (Guided choice course units) - semester I b keuze
MSc Computing Science: Intelligent Systems and Visual Computing  (Compulsory course units) 2 semester I b verplicht
MSc Computing Science: Software Engineering and Distributed Systems  (Guided choice course units) - semester I b keuze
MSc Mathematics: Science, Business and Policy  (Science, Business and Policy: Statistics and Big Data) - semester I b keuzegroep
MSc Mathematics: Statistics and Big Data  (MSc Mathematics: Statistics and Big Data) - semester I b keuze
ReMa Taalwetenschappen / Linguistics  (ReMa Language and Communication Technologies (LCT); Erasmus Mundus) 1 semester I b keuzegroep