 |
| Detailed information |
| Original study plan |
Master's programme Artificial Intelligence 2019W |
| Objectives |
Deep learning is a machine learning technique based on artificial neural networks. In this lecture, students will see more advanced insights, extensions and applications of deep learning, as well as discuss unsupervised deep learning techniques and open research questions. It is expected that students visiting this class already have a solid understanding of machine learning.
|
| Subject |
- Energy-based models (RBMs & Deep Boltzmann machines)
- Unsupervised Deep Learning (VAEs, GANs, Flows)
- Bayesian Deep Learning (Gaussian Processes, Evidence Framework & modern bayesian approaches)
- Interpretability in Deep Learning (Saliency methods, deep dream, visualizing CNNs, …)
- Error Surfaces (Flat minima, effects of deepness, issues in generalization)
|
| Criteria for evaluation |
Exam at the end of the semester
|
| Methods |
Slide presentations, discussions, and code examples
|
| Language |
English |
| Changing subject? |
No |
|
