Techniques of AI

Geraint A. Wiggins
Course description
Course Content:
  • Brief introduction to AI (with focus on search spaces and planning)
  • Learning of concepts (version spaces and decision trees)
  • Instanced based learning
  • Reinforcement Learning
  • Bayesian Learning
  • Neural Networks
  • Evaluation of hypotheses: confidence, bias variance trade off
  • Computational learning theory
  • Evolutionary algorithms
Learning Outcomes:
  • Knowlegde and insight:
    The student is acquainted with the most commonly used AI techniques, including learning algorithms.
    The student can correctly trace a learning algorithm on a small data set or environment.
    The student is capable of applying evaluation techniques to estimate the performance of the obtained results and to calculate the performance of an algorithm given a concrete application context.
  • The use of knowledge and insight:
    The student can explain the outcome of a given algorithm when applied in a given setting.
    The student is able to choose the appropriate techniques given a concrete learning problem, to apply them correctly and to evaluate the obtained results.
  • Judgement ability:
    The student must be able to devise and sustain arguments in favor of against some choice of (learning-) technique for a given problem.
  • Communication:
    He/she can motivate the chosen approach to specialist and non specialists.
  • Skills:
    Students have obtained the skills to autonomously develop, program, analyse, and apply learning techniques to a wide variety of problems.

All detailed and official information about the course here >