Messages

Hi everyone!

We have added two more repetition group sessions. The updated list of sessions will be as follows:

• Wednesday May 8, 10:15 - 12:00, Datastue Limbo: Practical Issues in Supervised Learning (bias, overfitting, crossvalidation, etc)
• Wednesday May 8, 12:15 - 14:00, Datastue Limbo: Repetition session on Reinforcement Learning
• Friday May 10, 12:15 - 14:00, Seminarrom Sed: Repetition session on Unsupervised Learning
• Monday May 13, 14:15 - 16:00, Datastue Assembler: Repetition session on Supervised Learning (focus on evaluation and algorithms)
• Tuesday May 14, 14:15-16:00, Datastue Limbo: Search and Evolutionary Algorithms
• Friday May 24, 12:15-14:00, IT-seminarrom Sed: Neural Networks - From basics to deep learning architectures

We encourage you to join these sessions if you need a little repetition of the covered topics before the exam.

-Kai

We were asked which formulas one is supposed to know for the exam.  You can find an overview of the required formulas here.

It can also be found in the Practical Information section.

Hi everyone!

Some of the next week's group sessions will be focused on repeating selected topics from the course syllabus. The list of sessions will be as follows:

• Wednesday May 8, 10:15 - 12:00, Datastue Limbo: Practical Issues in Supervised Learning (bias, overfitting, crossvalidation, etc)
• Wednesday May 8, 12:15 - 14:00, Datastue Limbo: Repetition session on Reinforcement Learning
• Tuesday May 14, 14:15-16:00, Datastue Limbo: Search and Evolutionary Algorithms
• Friday May 24, 12:15-14:00, IT-seminarrom Sed: Neural Networks - From basics to deep learning architectures

We encourage you to join these sessions if you need a little repetition of the covered topics before the exam.

-Kai

Hi everyone! In this week's intereactive session, we will have a visit from Dongho Kwak, who will talk about his practical experience with working on Ethics in AI, in the ENACT project.

Hi everyone!

Unfortunately the group session for group 3 (Friday at 12:15) has to be cancelled due to illness. Feel free to visit any of the other groups if you need help with assignment 3!

-Kai

Hi everyone!

We made a small update to assignment 3, to clarify a bit how to perform the quantitative assessment of k-means. This is just an update of the explaining text, so if you prefer to use the notebook we previously distributed for assignment 3, that is also totally fine. You can see the updated version in the mandatory exercises page now.

-Kai

Hi everyone!

This coming Thursday (April 18) we are fortunate to have another visitor who is an expert in the week's topic! Kyrre Glette, from the group of robotics and intelligent systems will join us to talk about how to use inspiration from nature when designing and building robots - and in particular, how to use principles from natural evolution to optimize robots. Hope to see you there!

-Kai

Hi everyone!

This week's interactive session will have a guest lecture from Elliptic Labs, who will talk about their work on classification of sensor data using deep neural networks. Hope to see you there for a look at how state-of-the-art AI methods can be applied in practice!

-Andrey and Kai

Dear IN3050/4050 students,

Mandatory Assignment 3, with deadline April 26, is now online - see the Mandatory Assignments-folder. Good luck, and as always we encourage you to visit a group session for assistance with the assignment.

-Kai

Hi everyone!

In this and the next 2 weeks, we will have visits from experts on topics related to the weekly syllabus in the interactive session. The first one, on Thursday April 4th, is postdoctoral researcher Benedikte Wallace, who will talk about how to apply unsupervised / self-supervised learning for modelling dance movements. See some more info below - hope to see many of you there!

-Kai

--------------

Benedikte will talk about her work on using deep learning to generate dance movement using a dataset of motion capture data. Her work uses sequence prediction models such as the Transformer and the RNN to predict the next position of the dancer¡¯s body. While these models learn the most likely positions from the data, there are many poses that might be a good fit!

How do we decide what makes a good dance move? What makes something interesting or beautiful? In this lecture we will look at some...

The deadline for submitting your peer2peer reviews for mandatory 1 is extended till March 26, 2024.

This is due to the experimental nature of this task and due to the fact that it is the first time we conduct it. The deadline for the 2nd mandatory will be strict (April 29th).

We remind again that peer2peer review is an obligatory part of the assignment for both the reviewer and the one under review. If you do not submit the review for Mandatory 1 by the deadline, your submission for Mandatory 2 can be outright rejected. Note that the interview session can be in-person or online: this is completely up to you.

...

Hi everyone!

Most of you should now have been assigned your peer for the peer review (those with extended deadlines/extra attempts for the mandatory exercise may take a bit more time to distribute). We recommend that you check your email regularly the next days, in case your peer is trying to get in touch with you.

Note also that it is absolutely fine to do you peer2peer review online, via Zoom or any other video-conferencing software you prefer.

Thanks!

-Kai

Hi everyone, We will host another session on mathematics useful for this course 12:00-14:00 on Tuesday 12.03.24 in the room Limbo. We will be covering derivatives, partial derivatives, gradients and how this relates to loss functions and learning in supervised learning. This session will primarily be relevant for those with limited math background, so if you have taken mathematics courses at the university level you will likely have limited benefit from this session.

Looking forward to seeing you Victor Prometheus Drachensteen

Hi everyone,

This Friday (01.03.24) we will have an extra group session covering some mathematics that will be very useful for understanding the Supervised Learning part of the curriculum. In the session of Friday we will be covering Linear Algebra and some foundational Statistics.

In this course we have students with very different backgrounds. This session is primarily for those students with limited mathematical background (Language Technology, Design, ?rsstudium..). Those students that have taken university-level mathematics courses (Robotics, Data Science, Mathematics¡­), will have limited utility from this session. If you are wondering if the session will be useful for you.. take a look at this document (...

Hi everyone!

Unfortunately today's group session has to be cancelled due to illness. Those of you planning to go there are encouraged to visit one of the other groups later this week.

Have a nice week!

-Kai

Hi!

If you are struggling with getting started with Mandatory Exercise 1, our group teacher Tobias made a getting started-document, which we have shared here.

Have a nice weekend!

-Kai

Please check the guidelines for peer-to-peer code review of the obligatory assignments.

The aim of peer-to-peer assessment is to enable the students to demonstrate their understanding by discussing segments of their code with a peer reviewer (another student). While students are permitted to utilize smart assistants (e.g., generative language models) to assist with mandatory assignments, it is imperative that the students still comprehend their code thoroughly.

The peer-to-peer evaluation is conducted for every mandatory assignment of the course - thus, 3 times. The review is a simple PDF file with a few words filled in (see the template at the link above). The deadline for the nearest peer evaluation results submission (attached to obligatory 1) is March 21st.

The first mandatory exercise is posted online, here. The deadline is February 23rd. Note that for master-level students (IN4050) there is an extra task, which is optional for IN3050-students.

Good luck!

Hi everyone!

The course forum is available here:

https://astro-discourse.uio.no/c/in3050-24v/

Feel free to ask any questions you may have about the course there.

-Kai

Hi everyone!

For those of you who want to read up on the mathematical concepts we will meet later in the course, I added a note written by previous course teach Jan Tore here.

See you!

-Kai