Intelligent Systems Department
This course provides a comprehensive exploration of modern deep learning techniques, from foundational concepts to advanced topics such as transformers, graph learning, multimodal systems, and generative models.
- Neural network optimization & regularization
- Convolutional Neural Networks (CNNs)
- Recurrent Neural Networks (RNNs), LSTMs, GRUs
- Attention mechanisms & Transformers
- Computer Vision: classification, detection, segmentation
- Reinforcement Learning (RL)
- Generative Models: VAEs, GANs
- Graph Neural Networks
- Multimodal Learning
| Week | Topic | Lecture | Seminar | Recording |
|---|---|---|---|---|
| 1 | Multi-layer perceptron. Gradient calculation | - | - | - |
| 2 | NN optimization. Regularization | - | - | - |
| 3 | Weight initialization. Batch normalization. CNN | - | - | - |
| 4 | RNNs, LSTM, GRU, State Space Models | - | - | - |
| 5 | Attention, Transformer, BERT | - | - | - |
| 6 | Computer Vision: Classification & Detection | - | - | - |
| 7 | Semantic & Instance Segmentation | - | - | - |
| 8 | Reinforcement Learning I | - | - | - |
| 9 | Reinforcement Learning II | - | - | - |
| 10 | Graph Learning | - | - | - |
| 11 | Generative Models: VAE | - | - | - |
| 12 | Autoregressive Models & GANs | - | - | - |
| 13 | Multimodal Learning | - | - | - |
All lecture and seminar recordings are available on the Machine Learning — Intelligent Systems YouTube channel.
We encourage students and collaborators to contribute to this repository by:
- Submitting issues for bugs or suggestions
- Creating pull requests for improvements
- Sharing additional resources or notebooks
This repository is licensed under the MIT License — see the LICENSE file for details.