Machine Learning (incl. Deep Learning) (4174) |
| Credits: 6,0 | | Study load hours: 162 | Period: semester 2 (6sp)  |
| Language of instruction: English | | Exam contract: not possible |
|
|
The student can program fluently.
The studen has basic knowledge of statistics and linear algebra.
|
|
|
|
|
The course will focus on explaining why deep learning architectures work, connecting optimization, generalization, and representations, and giving students a mental map of modern ML research.
During the course, we will discuss, among other topics:
- The missing foundations (generalization, optimization, regularization,...)
- Deep NN architectures
- Convolutional NN
- Transfer Learning
- Attention and transformer models
- Reinforcement learning
Students acquire basic knowledge about the theoretical background of the techniques and are able to apply them practically in mini-projects where they can explain and present the acquired results.
|
|
| Compulsory course material |
| |
Course slides and copies of articles. The course material is distributed during the class or made available via the web (Blackboard) . |
|
|
|
|
|
|
|
|
|
Lecture ✔
|
|
|
|
Practical ✔
|
|
|
|
Project ✔
|
|
|
|
Self-study assignment ✔
|
|
|
|
|
|
|
|
Exercises ✔
|
|
|
|
Presentation ✔
|
|
|
|
Report ✔
|
|
|
|
Semester 2 (6,00sp)
| Evaluation method | |
|
| Written evaluation during teaching period | 30 % |
|
| Transfer of partial marks within the academic year | Yes, with condition |
|
| Conditions transfer of partial marks within the academic year | Minstens 50% behaald. |
|
|
|
|
|
|
|
|
|
| Oral evaluation during teaching period | 20 % |
|
| Transfer of partial marks within the academic year | Yes, with condition |
|
| Conditions transfer of partial marks within the academic year | Minstens 50% behaald. |
|
|
|
|
|
|
|
|
|
|
| Evaluation conditions (participation and/or pass) | ✔ |
|
| Conditions | The student must take part in all parts of the assessment |
|
|
|
| Consequences | If the conditions are not met, the mark achieved will be capped at 7. |
|
|
|
| Additional information | For resits, the student(s) must retake only the part for which they failed. If this concerns the evaluation during the semester, the student will have to complete both the assignments, the project and the paper presentation. |
|
Second examination period
| Evaluation second examination opportunity different from first examination opprt | |
|
|
Learning outcomes | EC = learning outcomes DC = partial outcomes BC = evaluation criteria |
Master of Computer Science
|
- EC
| EC 1: A graduate of the Master of Computer Science programme has insight into the most important technological developments in the field of computer science and the underlying scientific principles. | - EC
| EC 5: A graduate of the Master of Computer Science programme is able to independently model a complex problem in computer science, to introduce the necessary abstractions, to describe and to implement the solution in a structured manner, and, finally, to discuss with the stakeholders why the chosen solution and the corresponding implementation meet with the specifications. | - EC
| EC 6: A graduate of the Master of Computer Science programme is able to independently situate a scientific problem, analyse and evaluate it, to formulate a research question and propose a solution for this in a scientifically substantiated manner. | - EC
| EC 8: A graduate of the Master of Computer Science programme is able to communicate information, ideas and solutions to an audience of fellow computer scientists and to non-specialists by expressing him or herself on the proper level of abstraction. | - EC
| EC 9: A graduate of the Master of Computer Science programme is able to clearly report both orally and verbally on his or her work in a national and international context. | - EC
| EC 10: A graduate of the Master of Computer Science programme is able to work in team; he or she is able to distribute and coordinate the activities through cooperation in small and large groups. |
|
|
|
|
| Included in these programmes | Tolerance3 |
|
|
Y
|
|
Master Computer Science profile Artificial Intelligence
|
Y
|
|
Master of Computer Science choice
|
Y
|
|
|
1 Education, Examination and Legal Position Regulations art.12.2, section 2. |
| 2 Education, Examination and Legal Position Regulations art.15.1, section 3. |
3 Education, Examination and Legal Position Regulations art.16.9, section 2.
|
|
|