Neural Networks: Theory and Implementation

Hi All,

The questions for Assignment #8 have been updated. For the programming assignment Q8.4, the fourth experiment was asked to be done with weight-decay and early-stopping, both enabled. There was a typo in the questions, where in one instance, it was mentioned only with early-stopping. We have uploaded a new updated version of the Assignment, please use that.

Also, a few of you may not have noticed, but Assignment #8 was also updated previously due to some dimensionality problems in Q8.2(b). At that time, 8.4 was also updated to make the requirements and instructions clearer. Please use the latest version to avoid any problems during grading.

Best Regards,

Monseej

Hi Everyone,

Just a heads-up, just like last week, we'll be holding today's Tutorial starting at 14:15 online via Microsoft Teams. If you plan to attend, please join this team's link:

https://teams.microsoft.com/l/meetup-join/19%3ameeting_MzY2ZThhNDYtYTMyMi00M2M5LWI4YjgtN2E1ZWRiYjliODM4%40thread.v2/0?context=%7b%22Tid%22%3a%2267610027-1ac3-49b6-8641-ccd83ce1b01f%22%2c%22Oid%22%3a%22c41ecae6-cb71-45d7-9ce8-3e33e8ed91f8%22%7d

 

Note: This will be the last online session we'll have (hopefully), from next week onwards, it will be in-person at  SR 016, E1 3.

 

Thanks and Regards,

Monseej Purkayastha

Hi,

yesterday I was asked for an old exam. Here is one: https://cms.sic.saarland/nnti_2425/dl/10/Old_Exam.pdf (also in the materials section).

Please note that it has very limited predicitve power about this years exam. The team is different and the assignments are different and this will certainly have an impact on this years exam.

Best,

Dietrich Klakow

 

Hi Everyone,

For all those who opted for the Friday afternoon Tutorial slot starting at 14:15, please join this team's link:

https://teams.microsoft.com/l/meetup-join/19%3ameeting_MzY2ZThhNDYtYTMyMi00M2M5LWI4YjgtN2E1ZWRiYjliODM4%40thread.v2/0?context=%7b%22Tid%22%3a%2267610027-1ac3-49b6-8641-ccd83ce1b01f%22%2c%22Oid%22%3a%22c41ecae6-cb71-45d7-9ce8-3e33e8ed91f8%22%7d

 

Thanks and Regards,

Monseej Purkayastha

Hi,

as announced today in the lecture we will have a 6th tutorial group in particular for those who have not yet been assigned to a tutorial yet. Here is a doodle with three alternatives:

https://doodle.com/meeting/participate/id/bqDzOp2a

Please doodle as soon as possible, latest by Thursday lunchtime (11:59 am).

Best regards,

Dietrich Klakow

Hi everyone,

By popular demand (and maybe a little peer pressure), here’s a lineup of recommended books to supercharge your course experience:

1. Deep Learning, Ian Goodfellow and Yoshua Bengio and Aaron Courville (also available online: https://www.deeplearningbook.org/)

2. Pattern Recognition and Machine Learning, Christopher Bishop

Both of these books are available in the library. Happy studying – or at least happy book-collecting!

Cheers,

Nhi

Dear students,

for those of you that missed last lecture,

• 60% of the points grants you the exam admission
• participating fruitfully in a tutorial, for example by presenting your solution to an exercise, grants you bonus points towards the exam admission.

Moreover, Assignment 2 has been released a couple of days ago, at the end of the lecture. The due date is 06/11/24 at 23:59.
From now on, the assignments will always be released at the end of the lecture and be due on Wednesday of the following week. 

Good luck!

Assignment 1 has been released. The release was delayed by one day because of the CMS system being down. In this special case, the deadline is extended by one day and this assignment will be due on 30th October 23:59. After this, all assignments will follow the regular schedule of being released at lecture time and being due before the lecture.
Best of luck