Deep Learning DSBA 2026/2027

2026-08-27T17:16:17Z

Ivmilova: Новая страница: «== Course Syllabus == DSBA Deep Learning 2026-2027. * DSBA (ПАД ФКН): [https://www.hse.ru/ba/data/courses/1163520628.html Syllabus] == Teachers and Assistants == {| class="wikitable" style="text-align:center" |- ! Role !! DSBA 241 !! DSBA 242 !! DSBA 243 !! DSBA 244 !! DSBA 245 !! |- || '''Lecturers''' | colspan="5" | [https://www.hse.ru/en/org/persons/223985242 Alexey Boldyrev], [https://www.hse.ru/en/staff/mekarpov Maksim Karpov], Lecturers' TA...»

== Course Syllabus ==

DSBA Deep Learning 2026-2027.

* DSBA (ПАД ФКН): [https://www.hse.ru/ba/data/courses/1163520628.html Syllabus]

== Teachers and Assistants ==

{| class="wikitable" style="text-align:center"
|-
! Role !! DSBA 241 !! DSBA 242 !! DSBA 243 !! DSBA 244 !! DSBA 245 !!
|-
|| '''Lecturers'''
| colspan="5" | [https://www.hse.ru/en/org/persons/223985242 Alexey Boldyrev], [https://www.hse.ru/en/staff/mekarpov Maksim Karpov], Lecturers' TA [https://t.me/rina_mlv Irina Milova]
|-
|| '''Seminarists'''
|| [https://www.hse.ru/en/staff/ aleksandr Aleksandr Khizhik]
|| [https://www.hse.ru/en/staff/sara Sara Ali]
|| [https://www.hse.ru/en/org/persons/401648437 Majid Sohrabi]
|| [https://www.hse.ru/org/persons/510407508/ Vsevolod Ovchinnikov]
|| [https://www.hse.ru/org/persons/510407508/ Vsevolod Ovchinnikov]
|-
|| '''Teaching Assistants'''
|| [https://t.me/chkapox Artur Karapetyan]
|| [https://t.me/lbananamanl Bogdan Uvarov]
|| [https://t.me/taravtaru Ivan Miniaitsev]
|| [https://t.me/d_poIy Polina Doronicheva]
|| [https://t.me/ksmnx Kirill Zykov]
|}

== Useful links ==

# [https://edu.hse.ru/course/view.php?id=283173 '''Smart LMS''']: for posting weekly material, grading quizzes, tests, and HW, etc.

# [https://drive.google.com/drive/u/1/folders/1eMMSxpG1rw6snyr6yrAkkke2a3AXgFZU '''Google Drive''']: for release of seminar Colab notebooks, lecture presentation slides, Starter Colab files for Kaggle competitions.

# [https://colab.research.google.com '''Google Colaboratory''']: for individual manual-graded assignments, group Kaggle assignments and reproducible seminar’s notebooks.

* We require the use of LaTeX and Markdown syntax for all write ups.

# [https://www.kaggle.com '''Kaggle.com''']: for data science competitions in teams of 1-3 students.

* Ensure that your name & surname match exactly to those in Smart LMS or we can lose you in grade matching. Update the profile with your presentable photo to help us authenticate you and credit your effort.

# Telegram Сhat (the link is in Smart LMS): for the course announcements (HW, timetable changes, etc.).

== Course Description ==

The course is dedicated to studying deep learning, which is the most rapidly developing field of machine learning. The course attendees will learn what kinds of machine learning tasks can be solved using neural networks and what types of neural networks are currently in use. The course has a clear practical focus, students will have to train neural networks on the various frameworks using the Python programming language. The course also covers tasks related to images and texts.

== Grading System ==

Relevant grading formulas are presented on the official course home page ([https://www.hse.ru/ba/data/courses/1163520628.html, DSBA Deep Learning]).

* DSBA
'''0.15 * Hackathon (Exam) + 0.25 * Kaggle competitions + 0.2 * Home assignments + 0.2 * Midterm Test + 0.2 * Quizzes'''

We use [https://docs.moodle.org/311/en/Grade_aggregation natural grade aggregation] in LMS. Rounding [https://en.wikipedia.org/wiki/Rounding#Rounding_to_the_nearest_integer to the nearest integer] is used to report 0-10 scale grades to HSE.

=== Homework (HW) Assignment ===

* HW is released via Moodle/Smart LMS and is also announced in the Telegram Channel.
* '''Individual''': These are individualized (not in groups!) assignments of two kinds
** Auto-graded assignments (thanks to STACK plugin with Maxima CAS backend). Some written responses will be selectively hand-graded by TAs.
** Quick Maxima syntax is provided below and in each assignment.

* Manual-graded assignments include analysis of datasets, analytical and conceptual problems, and programming assignments.
** All text explanations must be written in Markdown cells.
** Graders leave feedback in Smart LMS and execute Jupyter notebook to reproduce your results.
* '''Group''': Students are self-assigned into groups to compete on Kaggle.com. Teamwork is evaluated by instructors. Team’s grade is awarded to everyone on a team.

=== Midterm and Final Test ===

# We will have a cumulative in-class midterm test/exam in the middle and at the end of the semester (during the [https://www.hse.ru/en/studyspravka/grafik/ HSE examination sessions]). Do not book travel tickets that conflict with test dates.
# Moodle/Smart LMS based in Safe Exam Browser.
# Tests and exams are individual, i.e. no collaboration. Generative models, web searching, lecture and/or seminar materials, and textbooks are not allowed.
# Test questions are drawn from quiz banks, not HW. HW deepens your understanding, but a test measures it.
# There is a free navigation between questions, i.e. you can move back or forward the test questions.
# Results will be announced after the midterm test/exam within 5 working days.

=== University of London (UoL), Course ST3189 (ML) ===

1. Coursework Project in Python (or R) programming language is for DSBA students only and is administered by LSE/UoL. It is released around January and is due around April 1. Although students are given a 3-4 months window, this exercise is meant to be completed in a few days. Typically, students work on it in Feb/Mar. More details on the [https://emfss.elearning.london.ac.uk/ UoL site].

=== ~5 minute Quizzes during seminar in LMS ===

# Only students present in the classroom during the seminar are allowed to take the quiz. At the beginning of the seminar the seminar assistant will remove absent student(s) from the group list in moodle settings for the current quiz.
# Quizzes are conducted in Safe Exam Browser.
# Quizzes are based on lectures, seminars, textbooks, and other material delivered via our course.
# Quizzes individualized (shuffled and sampled from question banks) for each student. Most questions are auto-generated.
# All choice questions are [https://docs.moodle.org/311/en/Multiple_Choice_question_type#Multiple-answer_questions, multiple-choice] (regardless of singular/plural formulation). Incorrect answers lower your score to prevent guessing.
# Numeric answers are typically accepted with 0.01=1% of error, i.e. round to at least 4 decimal places, if needed. Please do not round any intermediate calculations. It’s best to use as many decimals as fits in the answer box.
# The quiz answers are released after all groups write the quiz .
# We always use [https://en.wikipedia.org/wiki/Natural_logarithm natural logarithm] (inverse of exp()) in this course.

=== Kaggle Competitions and Hackathon ===
# The assignment is conducted in the form of a kaggle competition in teams of 1-3 students.
# Leader Board (LB) position below or equal baseline (BL) results in 0 points in LB category.
# Above baseline is split into 4 quartiles: 1Q (top 25%), 2Q (top 50%), 3Q (top 75%), 4Q (bottom 25%).

=== Deadline Extensions and Makeup ===

# Only valid verifiable excuses are accepted for 1-2 day extensions.
#* DSBA students: submit your doctor's note via student services/study office.
# If you miss a deadline (with a valid/verifiable excuse), contact instructors ASAP to arrange a new deadline.
# Submissions are not allowed after the solutions have been released.
# Any test/exam retakes will be rescheduled as per university policy (see also dedicated rubric)
# Note: accommodating exceptions is difficult and time consuming. Typically, a verifiable medical emergency is a valid reason, but travel and conferences are not. It is the student's responsibility to start their work early, so as to hedge against any unforeseeable life event.

Wiki - Факультет компьютерных наук - Вклад [ru]

Deep Learning DSBA 2026/2027