Intendierte Lernergebnisse
Students should understand the different types of algorithms, comprehending the intrinsic differences and having an introductory view on all aspects of AI. The focus in the first half of the semester will be on reasoning under uncertainty, whereas the second half will deal with supervised and unsupervised machine learning methods. In this course, there will be a particular focus on neural networks, including fully connected networks, CNN and Transformers.
Lehrmethodik
The course consists on a mix between theoretical lectures and practical exercises. After every lecture on a topic, you will have an exercise sheet assigned to do at home, and a small minitest (15 minutes) will take place during the next lecture. The will be no programming exercises during this course. Lectures will be in presence, with no online option unless specified otherwise. The presence is not compulsory, but the minitests will be in presence (no online option), therefore you should be present at least in the days when minitests are held. Slides and teaching will be in English.eLearningMoodle
Inhalt/e
Provides an introduction to selected methods for dealing with uncertainty in Artificial Intelligence and Knowledge-Based Systems.TopicsUncertainty in AI SystemsBayesian Inference and Bayesian Networks"Classic" Machine LearningNeural NetworksCNNTransformersUnsupervised learning
Literatur
Adnan Darwiche. Modeling and Reasoning with Bayesian Networks. Cambridge University Press. 2009 P. Tan, M. Steinbach, V. Kumar. Introduction to Data Mining. Pearson. 2006 Stuart Russell and Peter Norvig: Artificial Intelligence: A modern approach. Prentice Hall, 2009 Judea Pearl: Probabilistic Reasoning in Intelligent Systems - Networks of Plausible Inference. Morgan Kaufmann Publishers, Inc. 1988 D. Koller, N. Friedman. Probabilistic Graphical Models: Principles and Techniques. The MIT Press. 2009 D. Barber. Bayesian Reasoning and Machine Learning. Cambridge University Press. 2012 T. Mitchell. Machine Learning. McGraw Hill. 1997Josh Starmer, The StatQuest Illustrated Guide To MachineLearning, 1stEdition. 2022.