Deep learning (2025/2026: Periode 4)

Bekijk rooster Print deze pagina

Cursusdoel

After completing this course, the student:

ILO1: Understands, is able to explain and analyze fundamental deep learning concepts, including optimization methods, regularization techniques, and computational graphs.

ILO2: Compare and evaluate different deep learning architectures for given problem settings.

ILO3: Apply and adapt deep learning models to given problems, including data preprocessing and model selection.

ILO4: Evaluate model performance, and limitations.

ILO5: Design and justify architectural and training choices for a given problem


Assessment:
The course is graded through one to three group projects (together 40%) a final exam (60%). The course can only be passed if at least a 5.0 is obtained in the final exam. To qualify for a repair of the final result the mark needs to be at least a 4.

Vakinhoudelijk

In this course we study deep learning models.

The subjects covered are:

Introduction to Deep Learning (Lecture1)
Computational Graphs and Automatic Differentiation (Lecture 2)
Optimization Techniques for Neural Network Training (Lecture 3)
Convolutional Neural Networks (CNNs) and Applications (Lecture 4 and 5)
Visualisation of Neural Networks (Lecture 6)
Recurrent Neural Networks (RNNs), LSTMs, and Transformers (Lecture 7)
Graph Neural Networks (GNNs) and Uncertainty Quantifications (Lecture 8)
Deep Learning Applications: Case studies (Lecture 9)
Self-Supervised learning and application (Lecture 10)
Deep Learning Applications: Case studies (Lecture 11)
Deep Neural Kernel Machines (Lecture 12)

Course form
Lectures and computer lab sessions.

Literature
Ian Goodfellow, Yoshua Bengio and Aaron Courville, "Deep Learning", MIT Press, 2016. http://www.deeplearningbook.org.

Christopher M. Bishop and Hugh Bishop, "Deep Learning - Foundations and Concepts", Springer 2025.

Possibly additional literature in the form of research papers, book chapters, etcetera.

Generative AI recommendation
The use of generative AI tools is permitted. Students are required to clearly document and briefly reflect on any use of generative AI tools in their assignments, including how the tools were used and how the final decisions and interpretations were made by the students.

Werkvormen

Hoorcollege

Werkcollege

Toetsing

Eindresultaat

Verplicht | Weging 100% | ECTS 7,5

Ingangseisen en voorkennis

Ingangseisen

Je moet een geldige toelatingsbeschikking hebben

Voorkennis

Knowledge of elementary linear algebra, (advanced) machine learning is presupposed.

Voertalen

  • Engels

Cursusmomenten

Gerelateerde studies

Tentamens

Er is geen tentamenrooster beschikbaar voor deze cursus

Verplicht materiaal

Er is geen informatie over de verplichte literatuur bekend


Aanbevolen materiaal

Er is geen informatie over de aanbevolen literatuur bekend

Coördinator

dr. S. Mehrkanoon s.mehrkanoon@uu.nl

Docenten

dr. S. Mehrkanoon s.mehrkanoon@uu.nl

Inschrijving

Deze cursus is open voor bijvakkers. Controleer wel of er aanvullende ingangseisen gelden.

Inschrijving
Van maandag 26 januari 2026 tot en met vrijdag 6 februari 2026

Na-inschrijving
Van maandag 30 maart 2026 tot en met dinsdag 31 maart 2026

Inschrijving niet geopend
Permanente link naar de cursuspagina
Laat in de Cursus-Catalogus zien
Laat in MyTimetable zien