| 23.9.2024 | Lec 1: Machine learning 101: model, loss, learning, issues, regression, classification | Intro: ML | Ales | - |
| 30.9.2024 | Lec 2: Under the hood of a linear classifier: two-class and multi-class linear classifier on RGB images | 1D regression and 2D classification: Revision of the regression and classification theory, analytic gradient computation, gradient in computational graph and loss minimization. | Karel | - |
| 7.10.2024 | Lec 3: Where the hell does the loss come from? MAP and ML estimate, KL divergence and losses. | Loss, MLP | Ales | HW1 - MLP |
| 14.10.2024 | Lec 4: Under the hood of auto-differentiation: Vector-Jacobian-Product (VJP) vs chainrule and multiplication of Jacobians, convolutional layer and its VJP | Backpropagation | Honza | - |
| 21.10.2024 | Lec 5: The story of the cat’s brain surgery: fully-connected NN + fast backpropagation via Vector-Jacobian-Product (VJP), cortex + convolutional layer | Convolutional neural networks | Honza | HW2 - Autograd |
| 28.10.2024 | Independence Day of Czechoslovakia | Preparation for midterm test | - | - |
| 4.11.2024 | Midterm test | HPC Tutorial | Roman | - |
| 11.11.2024 | Lec 6: Why is learning prone to fail? - Structural issues: layers + issues, batch-norm, drop-out | Optimization | Karel | - |
| 18.11.2024 | Lec 7: Why is learning prone to fail? - Optimization issues: optimization vs learning, KL divergence, SGD, momentum, convergence rate, Adagrad, RMSProp, AdamOptimizer, diminishing/exploding gradient, oscillation, double descent | Layers | Roman | HW3 - Segmentation |
| 25.11.2024 | Lec 8: Architectures, Transformers | Transformers | David Č. | - |
| 2.12.2024 | Lec 9: Transformers | Transformers | David Č. | HW4 - Transformers |
| 9.12.2024 | Lec 10: Reinforcement learning: Approximated Q-learning, DQN, DDPG, Derivation of the policy gradient (REINFORCE), A2C, TRPO, PPO, Reward shaping, Inverse RL, Applications, | Reinforcement learning I | David K. | - |
| 16.12.2024 | Lec 11: Implicit layers | Reinforcement learning II | David K. | HW5 - RL |
| 6.1.2024 | Exam | - | - | - |
