back to search

Scientific Computing and Machine Learning

CIT423000Elective Modules Informatics5 ECTSGerman/Englishwinter semesterDepartment Computer Science
AI-edited module sheet. Based on the TUMonline module description, edited for readability.Original in TUMonline

What it is about

You will learn how methods of Machine Learning are applied in Scientific Computing to solve problems from the natural sciences and engineering. The focus is on numerical approximations of differential equations, inverse problems, model reduction and practical implementation on CPU/GPU. In the end you will be able to understand mathematical formulations of dynamic systems and select appropriate learning algorithms for specific problems.

What you will be able to do

  • Foundations and mathematical formalism of Scientific Computing for ML
  • Description of dynamic systems (ordinary and partial differential equations)
  • Application of relevant software frameworks (numpy, scipy, tensorflow, pytorch, JAX, CUDA)
  • Evaluation of ML application areas in the natural sciences

What the module consists of

  • LectureConveying the fundamentals and the mathematical formalism
  • ExercisesDeepening and creative application of lecture content
  • HomeworkSelf-study to complement the lecture

Teaching method

  • Chalk lectureIn-depth conveyance of the fundamentals and the mathematical formalism
  • Slide presentationPresentation of current technical developments
  • Exercises and homeworkPromoting understanding and practical application
No dates in the current semester
There are no course dates for this module this semester, or they haven't been matched yet.

Module ratings

No ratings for this module yet.

Rate this module

Only fill in the categories you can judge – for each one, either stars and text together or nothing at all.

Lecture
Tutorial
Exam

Official page in TUMonline · Details are not binding.