Labs

Datum	Č.T.	S/L	Náplň	Učitel	Materiály	Úkol
22.-26.9.2025	1	L	Intro: Introduction to the course and machine learning.	Neumann L.
29.9-3.10.2025	2	S	1D regression and 2D classification: Revision of the regression and classification theory, analytic gradient computation, gradient in computational graph and loss minimization.	Pimenova O.	template_for_students.zip
6.-10.10.2025	3	L	Loss, MLP	Kučera A.		HW01 - MLP
13.-17.10.2025	4	S	Autograd: Computational graphs, backpropagation and the automatic gradient computation.	Vlk J.
20.-24.10.2025	5	L	CNN: Introduction to the convolution and convolution neural network.	Vlk J.		HW02 - Autograd
27.-31.10.2025	6	S	Training of neural networks	Hlavsa J.
3.-7.11.2025	7	L	Layers of Neural Networks	Hlavsa J.		HW03 - segmentation
10-14.11.2025	8	S	Optimization: Convergence rate, oscillations, diminishing gradients.	Pimenova O.
17.-21.11.2025	9	L	Holiday	-	-	-
23.-28.11.2025	10	S	Transformers I: Introduction to the transformer architecture, GPT2	Čapek D.
3.-5.12.2025	11	L	Transformers II: Intro into ViTs	Čapek D.		HW04 - Transformers
8.-12.12.2025	12	S	RL I Intro: Introduction to the reinforcement learning. Policy gradient.	Mrkos M.
15.-19.12.2025	13	L	RL II - Deep learning: Deep reinforcement learning.	Mrkos M.		HW05 - RL
5.-9.1.2025	14	S