Lectures
| Date | Week | Title | Resources |
|---|---|---|---|
| 24.09.2025 | 1 | Machine learning 101: engineering view on models, loss, learning, learning issues, regression, classification | 01_machinelearning101.pdf |
| 01.10.2025 | 2 | Linear classifier: two-class and multi-class linear classifier on RGB images | 02_linearclassifier.pdf |
| 08.10.2025 | 3 | Maximum Likelihood Estimation (MLE), KL Divergence: Where does loss function come from, why overfitting exists? | 03_maximumlikelihoodkldivergence.pdf |
| 15.10.2025 | 4 | Neural Networks: Perceptron, MLP, Backpropagation, Vector-Jacobian product, Autograd | 04_neuralnetworks.pdf |
| 22.10.2025 | 5 | Lecture cancelled (ICCV 2025) | |
| 29.10.2025 | 6 | The story of the cat's brain surgery: cortex + convolutional layer and its Vector-Jacobian-Product (VJP), fun with backpropagation | 05_cnns.pdf |
| 05.11.2024 | 7 | Midterm test | vir_2022_midterm_test.pdf vir_2022_midterm_solution.pdf vir_2022_training_questions_midterm_test.pdf dpl_2025_midterm_test.pdf Deep learning and Halloween:     |
| 12.11.2025 | 8 | Activation, Normalization and Regularization: activation functions, BatchNorm, Dropout, weight decay | 06_normalization.pdf |
| 19.11.2025 | 9 | Optimization: SGD, momentum, RMSProp, Adam | 07_optimization.pdf |
| 26.11.2025 | 10 | Backbone architectures: ResNet, EfficientNet, Transformers | 08_backbonearchitectures.pdf |
| 03.12.2025 | 11 | Task-specific architectures: Object detection, pose estimation, generative networks | 09_taskspecificarchitectures.pdf |
| 10.12.2025 | 12 | Reinforcement learning: Approximated Q-learning, DQN, DDPG, Derivation of the policy gradient (REINFORCE), A2C, TRPO, PPO, Reward shaping, Inverse RL, Applications, | |
| 17.12.2025 | 13 | Implicit layers: Backpropagation through unconstrained and constrained optimization problems, ODE solvers, roots, fixed points + existing end-to-end differentiable modules cvxpy, gradSLAM, gradMPC, gradODE, pytorch3d | |
| 07.01.2026 | 14 | Final test |