2023/2024 – Winter Term

This course will treat foundational topics in Machine Learning. The scheduled topics are: Bayesian ML, Analyses (PCA, LDA), Machine Learning Theory, Classification and Regression, Latent Variable Models.

The AQTIVATE workshop will focus on machine learning and is structured in two parts: Part I: Basic Machine Learning, from February 12th to 26th, 2024, and Part II: Machine Learning for Physics/Chemistry, from February 27th to March 1st, 2024. Final assignment due 1st April, 2024.

Computer programs can learn useful cognitive skills. This integrated lecture tries to communicate an intuitive understanding of elementary concepts in machine learning and their application on real data with a special focus on methods that are simple to implement. For a more advanced treatment we recommend the “Machine Learning 1” lecture or the “Lab Course Machine Learning”.

This course will treat deep Neural Networks in detail. Contents are optimization, applications and architectures of deep NNs.

This module is designed with the purpose of equipping students with a comprehensive grasp of the practical application of Machine Learning techniques in both academic and industrial scenarios. Unlike other modules that predominantly delve into methodologies, this module offers a holistic perspective on the complete lifecycle of a Machine Learning project.

Introduction to the Julia programming language and its Machine Learning ecosystem. Learn how to write reproducible, unit-tested Julia code for ML research in Julia. No prior knowledge of Julia is required.

The course focuses on built-in Python and applications relevant to machine learning primarily using NumPy (for efficient numerical computation) and Matplotlib (for visualization). It is not an introductory course to programming.

The goal of this course is to freshen and deepen the mathematical foundations from the computer science program that are necessary for the lectures Cognitive Algorithms and Machine Learning. Topics come from analysis (differentiation), linear algebra (vector spaces, dot products, orthogonal vectors, matrices as linear maps, determinants, eigenvalues and eigenvectors) and probability theory (multivariate probability distributions, calculations with expectation values and variances).

This course provides a series of lectures on probabilistic modeling and inference, covering the following topics: Bayesian learning, Gaussian process and Bayesian optimization, Variational inference, Generative modeling, Bayesian deep learning, Sampling methods.

The seminar provides an introduction to academic work. Students will learn how to give a presentation about a classical topic in Machine Learning, Please note that this seminar can only be taken together with CA or ML1/2-X.

Computer programs can learn useful cognitive skills. This course will take a closer look at specific applications of machine learning algorithms. With the help of their supervisors, students will read, understand, evaluate and present selected research papers on machine learning methods in different applications settings. At the end of the semester, each student will present their topic in a 15 min talk (+ 5 min discussion) in English.

This is a research-oriented seminar about applications of machine learning to quantum chemistry. Students will read, understand, evaluate and present selected research papers on machine learning methods in quantum chemistry. At the end of the semester, each student will present their topic in a 20 min talk (+ 10 min questions) in English. It is possible to attend this course without prior knowledge in chemistry or physics since many papers only require a basic comprehension of the respective research topic. There is no formal registration for the kick-off meeting. In the general case, it is not possible to take the seminar as a standalone course.

This is a joint research-oriented seminar of the Machine Learning Group and the Data Management Group. Throughout the seminar, students will have the opportunity to learn about recent advances in the intersection of Machine Learning and Data Management Systems. Interested students are required to participate in the kick-off meeting after which they will select, read, understand, and (if possible) programmatically evaluate one of the eligible papers (TBA), before giving a final 10-15 min presentation in the English language at the end of the semester. More details will be discussed during the Kick-off meeting. The Zoom-link for the Kick-Off meeting is written on the ISIS course-webpage.

This seminar consists of lectures by experts from science and industry who apply machine learning methods in their work. Possible topics include physical simulations, medical data analysis, modeling of neural signals, digital humanities, etc. Instead of a classroom exam, students will have to write a short technical report covering one of the talks at the end of the semester.

In this seminar, foundational and current research in the area of explainable machine learning (XAI) will be disseminated. Students present and discuss selected papers on XAI.

This seminar takes a closer look at a mix of hot topics in machine learning including, but not limited to: Deep Learning, Generative Models, Reinforcement Learning and Applications of Machine Learning.

Machine learning plays an important and growing role in neuroscience research. The two fields interact on different levels: ML provides tools for data analysis, ML can be used to model brain processes on different scales, and sometimes neuroscience even drives developments in ML. The purpose of the seminar is to cover the ML-neuroscience interaction from different angles, with a strong focus on research from/in Berlin.

Seminar on (deep) Generative Models, e.g. Variational Autoencoders, Generative Adversarial Networks, Normalizing Flows, Diffusion Models, etc.

Despite its central role in machine learning, many practitioners lack a solid fundamental understanding of probability theory. This reading group will cover the rigorous fundamentals of probability theory with a focus on developing mathematical fluency.