Quick links: [[https://intranet.fel.cvut.cz/en/education/rozvrhy-ng.B241/public/html/predmety/43/58/p4358506.html|Schedule]] | [[https://cw.felk.cvut.cz/forum/forum-1879.html|Forum]] | [[https://cw.felk.cvut.cz/brute/student/course/1508|BRUTE]] | [[https://cw.fel.cvut.cz/b231/courses/be5b33rpz/lectures/start|Lectures]] | ====== Labs ====== /* ** Winter semester 2023/2024 ** */ /* ** Important Links: ** * [[https://fel.cvut.cz/cz/education/rozvrhy-ng.B221/public/html/predmety/43/58/p4358506.html|course schedule]] * [[https://fel.cvut.cz/cz/education/rozvrhy-ng.B221/public/html/predmety/43/58/fsl-p4358506.html|RPZ students]] * [[https://cw.felk.cvut.cz/forum/forum-1792.html|Student forum]] (for reference: [[https://cw.felk.cvut.cz/forum/forum-1728.html|last]] and [[https://cw.felk.cvut.cz/forum/forum-1662.html|one before last year]] forum) - ** We do not use MS Teams for any communications!** * [[https://cw.felk.cvut.cz/sou/|Upload system]] * [[https://cw.felk.cvut.cz/brute/data/ae/release/2020z_rpz/rpz-2020/upload_system/rpz_leaderboard.php|Labs evaluation]] */ ===== Basic info ===== ** Where and when:** [[ http://cyber.felk.cvut.cz/contact/#maps | Building E on Charles square]], See [[https://intranet.fel.cvut.cz/en/education/rozvrhy-ng.B241/public/html/predmety/43/58/p4358506.html|RPZ Schedule]] If you are new to CTU, see the [[ http://cw.felk.cvut.cz/doku.php/help/for_visiting_students/newcommers | checklist for visiting students]]. /* ** EuroTeQ students ** (Monday 18.00 lab) : online meeting room https://feectu.zoom.us/j/6135640703 */ **What you may expect:** You will implement a variety of learning and inference algorithms on simple pattern recognition tasks. Each week a new assignment is introduced at the beginning of the lab, and you are expected to complete the task during the submission period. The discussion at the beginning of the lab session will link the theory presented in the lectures to the practical task in the weekly assignments. The remaining time of the lab is devoted to individual interactions between students and teaching assistants. See the detailed rules below. ** What do we expect: ** Basic knowledge of Python (check the links in the first lab's text if you need a help with this) and at least basic understanding of the respective lectures. ** Before you start: ** Make sure to complete you [[courses:be5b33rpz:labs:python_development|development environment setup]]. ** Teachers: ** * [[http://cmp.felk.cvut.cz/~sochmj1 | Jan Šochman]] () * [[https://cmp.felk.cvut.cz/~drbohlav | Ondřej Drbohlav]] () * [[https://cmp.felk.cvut.cz/~neumalu1/ | Lukáš Neumann]] () /* * [[https://cmp.felk.cvut.cz/~shekhovt | Alexander Shekhovtsov]] () */ /* ===== Student forum for assistance with assignments ===== There is a [[https://cw.felk.cvut.cz/forum/forum-1849.html|discussion forum]] administered for this course that can be used to solicit help for the assignments. It is monitored by the lab assistants and it is **the preferred form of communication** for giving assistance for the assignments since all students can see the question and answer threads. Please check the forum first if you have some confusion about an assignment. */ ===== Assignment plan ===== **Always download the latest template version before starting to work on a new assignment!** ^ Mon ^ Thu ^ Topic ^ Test ^ Extras ^ | 23.9. | 26.9. | [[courses:be5b33rpz:labs:01_intro:start|Introduction, work with python, simple example]] | | | | 30.9. | 3.10. | [[courses:be5b33rpz:labs:02_bayes:start|Bayesian decision task]] | | [[https://www2.math.upenn.edu/~mmerling/math107%20docs/practice%20on%20Bayes%20solutions.pdf|excercise]] | | 7.10 | 10.10. | [[courses:be5b33rpz:labs:03_minimax:start | Non-bayesian tasks - the minimax task]] | | [[https://docs.google.com/presentation/d/187eEwqwMsmBT4YqTAw-Zi-hptH09w6LA/edit?usp=share_link&ouid=116920526533647890213&rtpof=true&sd=true|Minimax for Normal distribution]] | | 14.10. | 17.10. | [[courses:be5b33rpz:labs:04_parzen:start | Non-parametrical estimates - parzen windows]] | * | | | 21.10. | 24.10. | [[courses:be5b33rpz:labs:05_mle_map_bayes:start | MLE, MAP and Bayes parameter estimation]] | | | | 28.10. | --- | no lab -- public holiday on Monday | | | | 4.11. | 7.11. | [[courses:be5b33rpz:labs:06_logreg:start | Logistic regression]] | | | | 11.11. | 14.11. | Problem solving / exam questions | | {{:courses:be5b33rpz:labs:rpzpractice_test2.pdf|practice tasks}} | | 18.11. | 21.11. | [[courses:be5b33rpz:labs:07_perceptron:start | Linear classifier - perceptron]] | * | | | 25.11. | 28.11. | [[courses:be5b33rpz:labs:08_svm:start|Support Vector Machine]] | | | | 2.12. | 5.12. | [[courses:be5b33rpz:labs:09_adaboost:start|AdaBoost]] | | | | 9.12. | 12.12. | [[courses:be5b33rpz:labs:10_k-means:start|K-means clustering]] | * | | | 16.12. | 19.12. | [[courses:be5b33rpz:labs:cnn:start|Convolutional neural networks]] | | | | 6.1. | 9.1. | Problem solving / exam questions | | | /* | 11.12. | 12.12. | --- | Expectation Maximization (only seminar, no lab) | | | */ There will be a short test at the beginning of the labs denoted with *. The questions in the tests will refer to material presented in prior lectures. ===== Exercises ===== In order to perform well in the lab tests and the exam it is important to follow the examples solved in the class and prepare by solving typical problems. We have prepared an initial version of an exercise book containing problems related to the lectures and labs and containing test examples from previous years with solutions. We update the text irregularly depending on our surplus. {{ :courses:be5b33rpz:labs:rpz_exercise_book.pdf |}} Please, report any issues or corrections to your teaching assistant. ===== Requirements to obtain the credit ("zápočet") ===== * Delivering all finished (= passing all checks in BRUTE) assignments until **the final deadline 12 Jan 2025** (see also BRUTE). * Attending the tests at the beginning of the *-labs. ===== Solution submission and evaluation ===== * A new assignment is introduced at each lab. * Students work on the assignment independently during the week, but are encouraged to discuss implementation problems or misunderstandings with the lab assistants either during the labs, by using the [[https://cw.felk.cvut.cz/forum/forum-1879.html|forum]], or via email or direct consultation during office hours. **The forum is the preferred form of communication.** * The submitted solution **must** be original work. Please see the [[http://cw.felk.cvut.cz/doku.php/help/common/plagiarism_cheating|plagiarism]] policy. Students must not make solutions to assignments available to anyone else. Credit will not be assigned in the case of plagiarism. * The solutions are delivered through the [[https://cw.felk.cvut.cz/sou/|Upload system]]. * There are templates prepared for all assignments with function headers and boilerplate code. The templates are available in a [[https://gitlab.fel.cvut.cz/B201_B4B33RPZ/rpz-python-assignment-templates|git repository]]. Template improvements in a form of a comment in the forum or merge / pull requests on the gitlab are very appreciated. * **During the labs** * a test is given on the denoted weeks, * a new assignment is introduced by a teaching assistant, and * the remainder of time is used to for discussion, problem solving and **bonus assignment evaluation**. * A successful solution is awarded **6 points** (4 points for the introduction lab) if it is delivered within two weeks from the assignment introduction. After two weeks the award is reduced to **5 points** (3 points for the first lab). * You are required to submit //all// assignments (all must pass BRUTE automatic evaluation) to receive the credit ("zápočet"). * After the final deadline (**12 January 2025**, see BRUTE) you will not be able to upload your solutions anymore. * Some assignments contain a **bonus task**. You can obtain up to **3 extra points** for each bonus task. Show us the solutions to the bonus tasks during the labs. They will be evaluated individually. Bonus tasks have no deadlines. They can be delivered at any time during the semester, up until the day before the exam. ===== Lab evaluation ===== * There are in total 64 available points from the assignments and another 36 points from the tests (12 points per test), so the total sum of the points is 100. * This does not include bonus points, so in principle you can get more than 100 points. * The points awarded from the labs correspond to 50% of the exam score, so they will be divided by 2 and used directly for the exam evaluation. * Bonus points will be considered if the student is on the borderline of a two grades. * The extra points may also compensate to some degree lost points during the exam test. However, accumulating a high score in the labs does not guarantee a good final mark; you must perform adequately on the written exam. In the case of an exceedingly poor result on the final written exam, the final evaluation will be made accordingly. /* * You can follow you actual score and compare your progress with others [[https://cw.felk.cvut.cz/brute/data/ae/release/2020z_rpz/rpz-2020/upload_system/rpz_leaderboard.php|here]]. */ ===== Absence ===== * If an absence is well-justified, you will be given a chance to take a make-up test. The conditions of compensation will be dealt with individually.