Online teaching

Online teaching

by Wulfram Gerstner -
Number of replies: 1

Dear Students of Biological Modeling of Neural Networks,

I am sorry that I could not actively participate in the teaching during the last 2 sessions. I have been sick with some unknown virus, but I feel better now.

The EPFL has shut down for good reasons: we need to slow down the spreading of the corona virus. More in another post.

Regarding the class and its transition to online teaching:

1. All lectures of the class are available as videos via several platforms. We have been hesitating between the moodle platform and EPFL courseware. We tested EPFL courseware yesterday, March 16. However, after further deliberations yesterday afternoon we decided that we will move back to MOODLE. Sorry, for the confusion.

In the future, all links to videos, all exercises and all additional information is available again on MOODLE. The MOODLE page of the course is the one that counts.

2. For the exercise session, we have tested yesterday the combination of slack and zoom. We found that it works well and is easy to handle. So from our side we will stick to this solutions.

3. The attendance of the exercise session yesterday was low. There could be several reasons for this

   (i) you have worked on the exercises together with friends in a smaller chat or video environment, separately from the main session

   (ii) everything was clear to you anyway and you did not need help with the exercises and had no questions for the lectures

  (iii) technical barriers of slack and zoom prevented you from joining

  (iv) you believe that since things are online you can do them later (such as at the end of the term).

If you fall in groups (i) and (ii) then everything is perfect. I don't insist that you attend the official TA session.  If you fall in group (iii), please tell Christos about it. If you are in group (iv), my advice is to get started as soon as possible. Pushing work to another week is not a good idea.

I hope you will get rapidly adjusted to the new online teaching mode. Please stay at home as much as possible. If you go for a walk, look for quiet streets. Do not go jogging along the lake shore: there are too many people. Talk with friends over video. Avoid any meeting in person (except those with whom you share an appartment anyway).

best regards

Wulfram Gerstner


In reply to Wulfram Gerstner

Re: Online teaching

by Felix Hans Michel Grimberg -

Dear Professor Gerstner,

I'm glad you're feeling better!

I posted in the discussion on courseware yesterday. I don't know if anyone is checking the discussion on courseware. I mean, I'll stick to moodle now that we're back on moodle :)

Anyway, my post was just a small remark about how the Closest Pattern (aka nearest neighbor) algorithm will generally fail for high-dimensional inputs such as vectorized images. This "Curse of Dimensionality" arises because points in high-dimensional space don't have any neighbors close-by unless the number of points grows exponentially with the number of dimensions. So, in my view, it might not be the best example to use at that point in the lecture, or maybe just the type of input (vectorized image) could be replaced by a lower-dimensional type of input.

Best regards,
Felix Grimberg

 P.S.: I fall into category (ii): The lectures were very clear and so I did not have any questions about the pen&paper exercises!