Website
Module Manual

Modul CS5071-KP12

Next Generation AI Computing and Learning (AIComLea)

Duration:


2 Semester
Turnus of offer:


starts every summer semester
Credit points:


12
Course of studies, specific field and terms:
  • Master Artificial Intelligence 2023 (compulsory), Artificial Intelligence, 1st semester at the earliest
Classes and lectures:
  • Stochastic Relational Modeling and Learning (lecture, 2 SWS)
  • Real-Time-Systems (practical course, 2 SWS)
  • Real-Time-Systems (lecture, 2 SWS)
  • Differential Probabilistic Programming (lecture, 2 SWS)
Workload:
  • 240 Hours private studies
  • 30 Hours work on project
  • 90 Hours e-learning
Contents of teaching:
  • Real-Time Systems: Real-time processing basics (Programmable Logic Controllers, Parallel processes) / Hardware platforms / Process interfaces / Real-time communication systems / Real-time programming / Process monitoring / Process control by using parallel state charts / Control systems design using Laplace transform / Real-time operating systems / Real-time middleware / Fault-tolerant real-time systems
  • Differential Probabilistic Programming: Introduction / Gradient descent / Deep networks and Deep learning / Autograd / Probabilistic Programming / Probabilistic Circuits (Grammar, Structural Constraints, Learning, Representation and Theory)
  • Stochastic Relational Modeling and Learning: Recap: Propositional modelling / Probabilistic Relational Models / Lifted inference (Lifted variable elimination, Lifted junction tree algorithm) / First-order knowledge compilation / Beyond standard query answering / Lifted learning / Approximate inference: Sampling / Sequential modelling and inference / Decision making
Qualification-goals/Competencies:
  • For all topics listed in the course content under the bullet points, students will be able to name the central ideas, define the relevant terms in each case, and explain how associated algorithms work using examples of applications.
Grading through:
  • portfolio exam
Responsible for this module:
Teachers:
Literature:
  • D. Koller, N. Friedman: Probabilistic Graphical Models - MIT Press, 2009
  • A. Katok, B. Hasselblatt: Introduction to the Modern Theory of Dynamical Systems - Cambridge: Cambridge University Press, 1995
  • G. Bolton: Programmable Logic Controllers - Newnes, 2009
  • I. Goodfellow, Y. Bengio, and A. Courville: Deep Learning - MIT Press, 2016
  • L. D. Raedt, K. Kersting, and S. Natarajan: Statistical Relational Artificial Intelligence: Logic, Probability, and Computation - Morgan & Claypool Publishers, 2016
  • B.J. Lurie, P. Enright: Classical Feedback Control with Nonlinear Multi-Loop Systems: With MATLAB® and Simulink® - 2019
  • E.N. Sanchez: Discrete-Time Recurrent Neural Control: Analysis and Applications - CRC Press, 2019
  • G. Barthe, J.-P. Katoen, A. Silva (Eds.): Foundations of Probabilistic Programming - Cambridge University Press, 2020
  • G. Van den Broeck, K. Kersting, S. Natarajan, D. Poole: An Introduction to Lifted Probabilistic Inference - MIT Press, 2021
Language:
  • offered only in English
Notes:

Prerequisites for attending the module:
- None

Prerequisites for the exam:
- 50% of online quiz points

Module exam(s):
CS5071-L1: Next Generation AI Computing and Learning portfolio exam for a total of 100 points, divided as follows:
- 50 points for an e-test (oral or written).
- 50 points for a project presentation

Letzte Änderung:
1.12.2023