Zima 2025 / Fall 2025
Handouts
| 2-INF-150: Strojové učenie / Machine Learning Zima 2025 / Fall 2025 Handouts |
|
Contact | Basic information | Homeworks | Exams | Handouts | Previous semesters
|
This page shows preliminary schedule of classes and servers as a repository
of materials relevant to class. The schedule will be update regularly
after lectures.
| ||
| Recommended literature | ||
|---|---|---|
|
In the schedule, we list the chapters most relevant to the material covered
in class. Presentation of the material in lectures usually differs from the
books. The book chapters should serve mainly as an additional materials for
self study. | ||
| ||
| Additional materials | ||
|
| Týždeň 22.09.2025-26.09.2025 | |
|
Administration. Introduction. Supervised learning / regression. Linear regression and it's variants. Literatúra: GBC:2.1-2.4 or B:C; GBC:5.1 or B:3.1 or HTF:3.1-3.2 |
|
| Slajdy: | Poznámky a ďalšie materiály: |
|---|---|
|
video intro: [ linka ] video regression: [ linka ] slides 1: [ PDF, 308 Kb ] slides 2: [ PDF, 342 Kb ] |
stanford (chapters 1, 2, 4): [ linka ] |
| Týždeň 29.09.2025-03.10.2025 | |
|
Theory of learning, overfit, underfit, bias variance. Tutorials 1: numpy Literatúra: GBC:4.3,5.9; B:3.1; Tutorials 1: collabora/jupyter notebooks, numpy |
|
| Slajdy: | Poznámky a ďalšie materiály: |
|---|---|
|
Tutorials 1: numpy: [ linka ] Learning theory notes: [ PDF, 362 Kb ] video lecture: [ linka ] |
stanford (chapter 4): [ linka ] stanford (chapter 1): [ linka ] |
| Týždeň 06.10.2025-10.10.2025 | |
|
Theory of learning cont. Regularization. Tutorials 2: regression |
|
| Slajdy: | Poznámky a ďalšie materiály: |
|---|---|
|
lecture: [ linka ] Tutorials 2: Regression: [ linka ] |
stanford (chapter 1): [ linka ] |
| Týždeň 13.10.2025-17.10.2025 | |
| Classification. Logistic regression, softmax (maximum entropy) classifier. Neural networks. | |
| Slajdy: | Poznámky a ďalšie materiály: |
|---|---|
|
lecture: [ linka ] |
stanford (chapter 3, 5 and 9.3): [ linka ] |
| Týždeň 20.10.2025-24.10.2025 | |
|
Support vector machines. Kernel trick. How to handle inseparable data. |
|
| Slajdy: | Poznámky a ďalšie materiály: |
|---|---|
|
lecture: [ linka ] lecture2: [ linka ] lecture3: [ linka ] |
SVM Stanford: [ linka ] |
| Týždeň 27.10.2025-31.10.2025 | |
|
Decision trees. Tutorials 3: neural networks |
|
| Slajdy: | Poznámky a ďalšie materiály: |
|---|---|
|
Tutorials 3: neural networks: [ linka ] lecture: [ linka ] |
Decision Trees: [ linka ] Decision Trees 2: [ linka ] My notes on decision trees: [ PDF, 193 Kb ] |
| Týždeň 03.11.2025-07.11.2025 | |
|
Bagging, random forests. Boosting, gradient boosting. Theory of learning 2 (PAC learning). |
|
| Slajdy: | Poznámky a ďalšie materiály: |
|---|---|
|
gradient boosting: [ linka ] My notes on gradient boosting: [ PDF, 230 Kb ] |
|
| Týždeň 10.11.2025-14.11.2025 | |
|
Theory of learning 2 - cont. (VC dimension). Tutorials: Decision trees and SVM |
|
| Slajdy: | Poznámky a ďalšie materiály: |
|---|---|
|
lecture: [ linka ] PAC learning rectangle game: [ linka ] PAC learing, VC dimension (until 50 minute): [ linka ] Tutorials 4: trees and SVMs: [ linka ] |
|
| Týždeň 17.11.2025-21.11.2025 | |
| Clustering. PCA |
| Týždeň 24.11.2025-28.11.2025 | |
|
How to build a language model? No lecture, faculty conference. |
| Týždeň 08.12.2025-12.12.2025 | |
|
Reinforcement learning. Recommendation systems. |
| Týždeň 15.12.2025-19.12.2025 | |
|
Vision models + transfer learning. Tutorials: PCA. |
| Týždeň 15.12.2025-19.12.2025 | |
|
Practical tips for machine learning. Tutorials: transfer learning, large models. |