This class is usually taught by Gerhard Widmer in the winter term. The class is taught in English.

Information for the current semester (if available):

Goals and Contents of this Class

The lecture gives an introduction to basic models and techniques in the field of Artificial Intelligence (AI). Specific topics to be covered include:

• Definitions of AI, history of AI, current state of the field
• Motivating scenario: autonomous intelligent "agents"
• Problem solving as a search process:
  • uninformed search algorithms
  • heuristic search algorithms
  • heuristic search in game playing
• Knowledge representation and logical inference:
  • Propositional logic
  • First-order (predicate) logic
  • Logic as a programming language: PROLOG
• Representing and reasoning with uncertain knowledge:
  • Basics of Bayesian probability theory
  • Knowledge representation and inference in Bayesian networks
• Basic notions of machine learning:
  • Learning logical definitions: inductive concept learning
  • Learning strategies for intelligent action selection: reinforcement learning
  • Learning about probabilities: logistic regression and neural networks
• Basic notions of computer perception

Teaching materials:

PDF versions of the Powerpoint slides used in the lecture will be made available via KUSSS (weekly).

Recommended reading (will not be needed if the lectures are attended on a regular basis):
Russell, S.J. and Norvig, P. (2000). Artificial Intelligence: A Modern Approach (2nd. Edition). Englewood Cliffs, NJ: Prentice-Hall. 
 

Exercise track (Übung)

The class is accompanied by an exercise track, in which the students will improve their understanding of the material by solving a series of theoretical and practical examples.

Be sure to also register for one of 344.021, 344.022, 344.023! 
 

Questions, suggestions, complaints, etc. to:

Gerhard Widmer, opens an external URL in a new window
Tel. 2468-4701 
gerhard dot widmer at jku dot at