15009 - Continuous Optimization for Artificial Intelligence Modulübersicht

Module Number: 15009
Module Title:Continuous Optimization for Artificial Intelligence
  Kontinuierliche Optimierung für Künstliche Intelligenz
Department: Faculty 1 - Mathematics, Computer Science, Physics, Electrical Engineering and Information Technology
Responsible Staff Member:
  • Prof. Dr. rer. nat. habil. Breuß, Michael
Language of Teaching / Examination:English
Duration:1 semester
Frequency of Offer: On special announcement
Credits: 6
Learning Outcome:

Upon successful completion of the module, students have gained in-depth knowledge of continuous optimization. They have a theoretical understanding of methods and algorithms. In addition, students are able to analyze and tackle relevant problems.

Contents:

Topics covered include:

  • first-order optimisation (gradient descent, adaptive moment estimation [ADAM]),
  • second-order optimization (Newton/quasi-Newton), as well as
  • Karush-Kuhn-Tucker conditions,
  • alternating direction method of multipliers [ADMM],
  • sparsity, and
  • duality.
Recommended Prerequisites:

Knowledge of the content of the module

  • 14015 Introduction to Mathematical Methods in Artificial Intelligence
Mandatory Prerequisites:None
Forms of Teaching and Proportion:
  • Lecture / 2 Hours per Week per Semester
  • Exercise / 2 Hours per Week per Semester
  • Self organised studies / 120 Hours
Teaching Materials and Literature:
  • M. P. Deisenroth, A. A. Faisal, and C. S. Ong: Mathematics for Machine Learning,  Published by Cambridge University Press, 2020.
  • S. Sra, S. Nowozin, S.J. Wright: Optimization for Machine Learning, The MIT Press, 2012.
  • S. Boyd, L. Vandenberghe: Convex Optimization, Cambridge University Press, 2004.

Further literature references will be provided at the beginning of the seminar.

Module Examination:Final Module Examination (MAP)
Assessment Mode for Module Examination:
  • Written examination, 90 min.
Evaluation of Module Examination:Performance Verification – graded
Limited Number of Participants:None
Part of the Study Programme:
  • Master (research-oriented) / Artificial Intelligence / PO 2022 - 1. SÄ 2024
  • Master (research-oriented) / Mathematical Data Science / PO 2025
Remarks:
  • Study programme Artificial Intelligence M.Sc.: Compulsory elective module in complex „Learning and Reasoning"
  • Study programme Mathematical Data Science M.Sc.: Compulsory elective module in complex „Fundamentals of Data Science"
Module Components:
  • Lecture: Continuous Optimization for Artificial Intelligence
  • Accompanying exercises
  • Related examination
Components to be offered in the Current Semester:
  • no assignment