Summer Term 2026

1300110401
Anmeldung ab 31.05.2026 möglich
Link to Registration

Content

DAY 1: short summary of python basics
DAY 2: classes and object oriented programming
DAY 3: accuracy & speed (general, not python only), parallelization & regular expressions
DAY 4: pandas, scipy for ordinary differential equations
DAY 5: some examples of machine learning (ML)

1300112309
Zu dieser LV existiert kein Anmeldeverfahren

1300132215
Anmeldung ab 01.03.2026 möglich
Link to Registration

Content

https://moodle.umm.uni-heidelberg.de/moodle/course/view.php?id=133

Goal

The participants will select a paper given in the Materials selection below and present the content to the group followed by a discussion.  Afterwards, the paper is summerized in a report.

1300132218
Anmeldung ab 01.03.2026 möglich
Link to Registration

Content

s. Module Handbook

Goal

s. Module Handbook

1300132219
Anmeldung ab 01.03.2026 möglich
Link to Registration

Content

s. Module Handbook

Goal

s. Module Handbook

1300132220
Anmeldung ab 01.03.2026 möglich
Link to Registration

Content

s. Module Handbook

Goal

s. Module Handbook

1300182201
Anmeldung ab 01.04.2026 möglich
Link to Registration

Content

https://sciai-lab.org/teaching/24s/gmlqc/

Goal

see https://sciai-lab.org/teaching/24s/gmlqc/

1300182202
Anmeldung ab 01.03.2026 möglich
Link to Registration

Content

This lecture introduces students to basic methods and techniques in computational statistics and data analysis, as widely applicable to empirical problems in the natural sciences. It provides an overview of relevant concepts and theorems in probability theory and mathematical statistics to modern deep learning techniques. The lecture is accompanied by computational exercises in Python or Matlab. It will enable students to analyze small and large data sets and interpret the results from a solid, theoretically grounded statistical perspective, to devise statistical & machine learning models of experimental situations, to infer the parameters of these models from empirical observations, and to test hypotheses about them.

1300182207
Anmeldung ab 01.03.2026 möglich
Link to Registration

Content

Please find all information here:

https://hci.iwr.uni-heidelberg.de/content/computer-vision

*** Formalities:

Teaching assistants (main point of contact): Friedrich Feiden: johann-friedrich.feiden@iwr.uni-heidelberg.de

Registration: Moodle: https://moodle.uni-heidelberg.de/course/view.php?id=25516


Prerequisite: no prerequisites, but it is recommended to have Machine Learning Background, e.g. Fundamentals of Machine Learning or equivalent

Exam: Either oral exam or mini-project (as in last years).
Leistungspunkte: 6 LP
Usability: Physics, MSc., Angewandte Informatik, MSc. Scientific Computing

Goal

Lernziele (erwartete Lernergebnisse und erworbene Kompetenzen): 	 - Brief Introduction to necessary Machine Learning (incl. U-Net, ResNet, Vision Transformers) - Basic Image Processing (incl. linear/non-linear Filtering) - Sparse feature Detection and Description (incl. SIFT and LIFT) - Projective Geometry, Epipolar Geometry - Sparse 3D Reconstruction , SLAM and Camera Localization - Neural Randiance Fields (NERF) - Robust Matching (incl. Differentiable RANSAC) - Object Tracking (incl. Particle Filter, Kalman Filter, ) - Object Recognition - Image Generation (incl. GAN, Diffusion, VAE, Flows) - Training Data Generation

1300182217
Anmeldung ab 01.03.2026 möglich
Link to Registration

Content

https://astroai-lab.de/sciml26.html