Laboratory for Applied Machine Learning Algorithms (LAMA)

Prerequisites

Basic programming skills are required. Solid knowledge of the basics of information technology as well as signal and system theory is also required. The lab provides the necessary know-how to understand and use the opportunities and challenges of AI in the future professional field.

Note: Registration takes place via the Wiwi Portal. Unfortunately, no Master's students can be admitted.

Content: Hands-on with real AI challenges

The relevance of machine learning and artificial intelligence (AI) in modern society is undeniable. This practical course offers students a sound, hands-on introduction to the methods and tools of machine learning.

We cover a broad spectrum - from analysis image processing to language processing and reinforcement learning.

The course offers:

• Implementation of basic algorithms (e.g. Perceptron, Decision Trees)

• Application of industry-relevant tools (e.g. PyTorch)

• Insights into the architecture and functionality of CNNs, RNNs and introduction to transformer models

• Use of powerful workstations for practical exercises

Procedure and project work

The course is divided into two parts. In the first lab sessions, you will work on given tasks in teams of two. These include programming tasks and theoretical questions that are solved in interactive Jupyter notebooks. The successful completion and submission of these task sheets is a prerequisite for participation in the oral colloquium at the end of the semester.

The second part is the "Into the Wild" section. Here you have the creative freedom to pursue your own project ideas or to participate in current research questions, for example we have already had projects that have dealt with everything from GeoGuesser to medical imaging.

The assessment is made up of the completed assignment sheets, the "Into the Wild" part and a colloquium. Attendance is compulsory for all dates and the preliminary discussion.

Procedure for laboratory sessions 1-8

• Preliminary discussion and group allocation

• Processing and analyzing data sets

• Basics of supervised learning

• Unsupervised learning

• Neural networks

• Basics of reinforcement learning and evolutionary algorithms

• Convolutional Neural Networks

• Transformers and Generative AI

Organizational matters and contents

Tutors wanted!

• Preliminary discussion and group assignment
• Processing and analysis of data sets
• Evaluation of ML systems
• Basics of supervised learning
• Unsupervised learning
• Neural networks
• Evolutionary algorithms
• Convolutional Neural Networks
• Recurrent Neural Networks and Transformer Models
• Into the Wild...

Procedure of the lab sessions 1-8

• During the individual lab sessions, students work on predefined tasks. These include programming tasks as well as tasks to be answered in text form.
• The task sheets are issued in the form of Jupyter notebooks. With this interactive development environment, you can test program codes directly in the task sheet, display solutions and complete the documentation or answers.
• After each laboratory session, the completed task sheet (the corresponding Jupyter notebook) is handed in.
• It is sufficient to hand in one copy of the notebook per group.
• Successful completion and submission of the task sheets is a prerequisite for participation in the oral colloquium at the end of the semester. Participants who fail to hand in their work will not be admitted to the colloquium!

Into the Wild...

• At the beginning of the second part, various data sets are presented, which are available for processing.
• Each group chooses one of the presented data sets, of course several groups can use the same data set. The problem is defined by the group itself. It is also possible to create your own problems for your own data sets.
• A concept for solving the problem is developed on the basis of what has been learned previously. This is implemented and tested.
• In addition to working on the data, it is also possible to optimize an existing approach for a data set in terms of runtime or latency. Among other things, an attempt can be made to achieve this using suitable hardware.
• Finally, each group prepares a presentation that introduces the developed concept and presents the results. A critical reflection of the previously made decisions will also be used to point out possible next steps.

Application procedure

This year, 30 places are expected to be offered for the lab.
You can register for the lab via the WiWi portal at the following link: https://portal.wiwi.kit.edu/ys/8270

Materials

The necessary materials for the LAMA will be made available via ILIAS. After successfully registering for LAMA, you will receive access to the tasks, data sets and additional information material.
The material is provided in English, but can be edited in German.

Tutors wanted

Former participants or Master's students who are interested in the topics can participate in the course as tutors. If you are interested, please send an e-mail with the appropriate subject to: lama∂itiv.kit.edu.

FAQ:

How do the lab sessions work?

During the individual lab sessions, students will work on predefined tasks. These include programming tasks as well as tasks to be answered in text form.

• The task sheets are issued in the form of Jupyter notebooks. With this interactive development environment, you can test program codes directly in the task sheet, display solutions and complete the documentation or answers.

• After each laboratory session, the completed task sheet (the corresponding Jupyter notebook) is handed in.

• It is sufficient to hand in one copy of the notebook per group.

• Successful completion and submission of the task sheets is a prerequisite for participation in the oral colloquium at the end of the semester. Participants who do not hand in their work will not be admitted to the colloquium!

What are the details of ItW?

• At the beginning of the second part, various data sets are presented, which can be selected for processing.

• Each group decides on one of the data sets presented; of course, several groups can also use the same data set. The problem is defined by the group itself. It is also possible to create your own problems for your own data sets.

• A concept for solving the problem is developed on the basis of what has been learned previously. This is implemented and tested.

• In addition to working on the data, it is also possible to optimize an existing approach for a data set in terms of runtime or latency. Among other things, an attempt can be made to achieve this using suitable hardware.

• Finally, each group prepares a presentation that introduces the developed concept and presents the results. The aim is to show possible next steps by critically reflecting on the decisions made previously.

I'm doing another Erasmus, can't be there for the last session, what now?

• Basically: Write us an email and let us know.

• If there are enough places, you can take part.

• If there are not enough places, we will prioritize.

• If you do not let us know when you register, you may not be able to complete the exam.