-
Notifications
You must be signed in to change notification settings - Fork 660
Homeworks and grading (HSE)
This course uses Anytask — a platform for uploading your solutions to course assignments. You can find the course page @ anytask at https://anytask.org/course/1205 , please use the invite codes in the table below:
| Group | Invite code |
|---|---|
| HSE: | PvNkg9T |
First thing you need to do is to register there. Just follow the link above and enter the appropriate code.
Deadlines for each assignment are set in 10 days from the corresponding seminar, unless explicitly specified otherwise. Assignments are added each week unless explicitly specified otherwise.
The course grade depends entirely on points obtained mostly by completing homework assignments. There will be no course exam at the end.
All assignments have descriptions in ./week*/README.md files like [this]
Almost all assignments will have a jupyter notebook handout and a “your code for X goes here” style problems. A fully and correctly implemented assignment yields 10 points (sometimes more, depending on the assignment). Doing something great on top of that yields bonus points.
Assignments are subject deadlines and will yield less points if submitted past deadline. In particular, submissions past deadline will be penalized by -1 point per day.
Homework can't yield negative amount of points, even if submitted 2 years past deadline.
Homeworks that got imperfect grade can (and should) be re-submitted with no additional lateness penalty.
If you think that you have a special circumstances (e.g. you got hospitalized) that prevented you from completing an assignment in time, ping course staff. We can cancel penalty for you.
One can use any languages/frameworks beyond the recommended one at his own risk. Srsly, if you’re not Andrej Karpathy or Volodymyr Mnih or something, at least consider the recommended way; Yes, we know that <your_language/framework_name> is infinitely superior in all aspects. So what?
Final grade is a sum of points, divided by 10 and rounded to the nearest integer. You cannot have a mark above 10.
The exact formula for rounding is
grade = min(10, max(0, round(float(points) / 10.0)))
If you wanna get really technical, this formula was obtained under python3.5.2 on ubuntu x64 with Core i7-3687U CPU and no one trying to hack it :)
There will be 11-14 assignments worth 10 points (more if you go beyond basic part). The "~14" part is due to us offering possible (but not guaranteed) 1-2 extra assignments depending on the chosen elective classes in the latter half of the course. Note that you do not have to pass every assignment to get the grade you want! Additionally (and very much optionally), if you are planning to research or build something cool related to deep learning, contact course staff via telegram to see if we can award points for that.
It's ultimately your decision, but we recommend that you pass all early homeworks (1-6), which would give you more freedom in the latter half of the course.