====== Lectures ======

^ Date ^ Week ^ Title ^ Resources ^
| 24.09.2025 | 1  |  __Machine learning 101__: engineering view on models, loss, learning, learning issues, regression, classification | {{ :courses:becm33dpl:lectures:01_machinelearning101.pdf}} |
| 01.10.2025 | 2  | __Linear classifier:__ two-class and multi-class linear classifier on RGB images | {{ :courses:becm33dpl:lectures:02_linearclassifier.pdf}} |
| 08.10.2025 | 3  |  __Maximum Likelihood Estimation (MLE), KL Divergence:__ Where does loss function come from, why overfitting exists? | {{ :courses:becm33dpl:lectures:03_maximumlikelihoodkldivergence.pdf}} |
| 15.10.2025 | 4  | __Neural Networks:__ Perceptron, MLP, Backpropagation, Vector-Jacobian product, Autograd | {{:courses:becm33dpl:lectures:04_neuralnetworks.pdf}} |
| 22.10.2025 | 5  | <fc #f00000>// Lecture cancelled (ICCV 2025) //</fc> | 
| 29.10.2025 | 6  | __The story of the cat's brain surgery:__ cortex + convolutional layer and its Vector-Jacobian-Product (VJP), fun with backpropagation | {{:courses:becm33dpl:lectures:05_cnns.pdf}}  |
| 05.11.2024 | 7  | **Midterm test** | {{ :courses:b3b33urob:lectures:vir_2022_midterm_test.pdf |}} \\ {{ :courses:b3b33urob:lectures:vir_2022_midterm_solution.pdf |}} \\ {{ :courses:b3b33urob:lectures:vir_2022_training_questions_midterm_test.pdf |}} \\ {{ :courses:becm33dpl:lectures:dpl_2025_midterm_test.pdf |}} \\ //Deep learning and Halloween:// \\ {{ :courses:becm33dpl:lectures:drawing01.jpg?100x100}} {{ :courses:becm33dpl:lectures:drawing02.jpg?100x100}} {{ :courses:becm33dpl:lectures:drawing03.jpg?100x100}} {{ :courses:becm33dpl:lectures:drawing04.jpg?100x100}} |
| 12.11.2025 | 8  | __Activation, Normalization and Regularization__: activation functions, BatchNorm, Dropout, weight decay | {{:courses:becm33dpl:lectures:06_normalization.pdf}}  |
| 19.11.2025 | 9  | __Optimization:__ SGD, momentum, RMSProp, Adam | {{:courses:becm33dpl:lectures:07_optimization.pdf}}  |
| 26.11.2025 | 10 | __Backbone architectures:__ ResNet, EfficientNet, Transformers | {{:courses:becm33dpl:lectures:08_backbonearchitectures.pdf}} |
| 03.12.2025 | 11 | __Task-specific architectures:__ Object detection, pose estimation, generative networks | {{:courses:becm33dpl:lectures: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** |