621.064 (24S) Introduction to Artificial Intelligence 2 - Group A
Overview
- Lecturer
- Course title german Introduction to Artificial Intelligence 2 - Group A
- Type Lecture - Course (continuous assessment course )
- Course model Attendance-based course
- Hours per Week 2.0
- ECTS credits 3.0
- Registrations 26 (30 max.)
- Organisational unit
- Language of instruction Englisch
- Course begins on 04.03.2024
- eLearning Go to Moodle course
Time and place
Course Information
Intended learning outcomes
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.
Teaching methodology
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.
eLearning
Moodle
Course content
Provides an introduction to selected methods for dealing with uncertainty in Artificial Intelligence and Knowledge-Based Systems.
Topics
- Uncertainty in AI Systems
- Bayesian Inference and Bayesian Networks
- "Classic" Machine Learning
- Neural Networks
- CNN
- Transformers
- Clustering algorithms
Literature
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. 1997
Josh Starmer, The StatQuest Illustrated Guide To MachineLearning, 1stEdition. 2022.
Examination information
Examination methodology
Written Exam at the end of the lectures + Minitests during the semester. There will be 6 minitests during the semester. 10 points per minitest. At the end of the semester, you must have collected at least 30 points to qualify for the exam. Points can be earned also through exercise demonstration and active participation in class
Examination topic(s)
All the topics treated during the lectures.
Assessment criteria / Standards of assessment for examinations
75% of the score will be given by the performance of the final exam. 25% comes from the performance achieved during the lectures, evaluated through mini-tests and participation.
Grading scheme
Grade / Grade grading schemePosition in the curriculum
- Bachelor's degree programme Applied Informatics
(SKZ: 511, Version: 19W.2)
-
Subject: Vertiefung Informatik
(Compulsory elective)
-
7.3 Einführung in die Artificial Intelligence II (
2.0h VC / 3.0 ECTS)
- 621.064 Introduction to Artificial Intelligence 2 - Group A (2.0h VC / 3.0 ECTS) Absolvierung im 4., 5., 6. Semester empfohlen
-
7.3 Einführung in die Artificial Intelligence II (
2.0h VC / 3.0 ECTS)
-
Subject: Vertiefung Informatik
(Compulsory elective)
- Bachelor's degree programme Applied Informatics
(SKZ: 511, Version: 17W.1)
-
Subject: Medieninformatik
(Compulsory elective)
-
4.2 Uncertain Knowledge: Reasoning and Learning (
2.0h VC / 4.0 ECTS)
- 621.064 Introduction to Artificial Intelligence 2 - Group A (2.0h VC / 3.0 ECTS)
-
4.2 Uncertain Knowledge: Reasoning and Learning (
2.0h VC / 4.0 ECTS)
-
Subject: Medieninformatik
(Compulsory elective)
- Bachelor's degree programme Applied Informatics
(SKZ: 511, Version: 17W.1)
-
Subject: Natural Language Processing
(Compulsory elective)
-
5.3 Uncertain Knowledge: Reasoning and Learning (
2.0h VC / 4.0 ECTS)
- 621.064 Introduction to Artificial Intelligence 2 - Group A (2.0h VC / 4.0 ECTS)
-
5.3 Uncertain Knowledge: Reasoning and Learning (
2.0h VC / 4.0 ECTS)
-
Subject: Natural Language Processing
(Compulsory elective)
- Bachelor's degree programme Applied Informatics
(SKZ: 511, Version: 17W.1)
-
Subject: Software Development
(Compulsory elective)
-
6.3 Uncertain Knowledge: Reasoning and Learning (
2.0h VC / 4.0 ECTS)
- 621.064 Introduction to Artificial Intelligence 2 - Group A (2.0h VC / 4.0 ECTS)
-
6.3 Uncertain Knowledge: Reasoning and Learning (
2.0h VC / 4.0 ECTS)
-
Subject: Software Development
(Compulsory elective)
- Bachelor's degree programme Applied Informatics
(SKZ: 511, Version: 17W.1)
-
Subject: Business Informatics
(Compulsory elective)
-
7.3 Uncertain Knowledge: Reasoning and Learning (
2.0h VC / 4.0 ECTS)
- 621.064 Introduction to Artificial Intelligence 2 - Group A (2.0h VC / 4.0 ECTS)
-
7.3 Uncertain Knowledge: Reasoning and Learning (
2.0h VC / 4.0 ECTS)
-
Subject: Business Informatics
(Compulsory elective)
- Bachelor's degree programme Management Information Systems
(SKZ: 522, Version: 20W.2)
-
Subject: Spezialisierung Angewandte Informatik
(Compulsory elective)
-
Spezialisierung Angewandte Informatik (
0.0h VO, VC, KS, UE / 6.0 ECTS)
- 621.064 Introduction to Artificial Intelligence 2 - Group A (2.0h VC / 3.0 ECTS) Absolvierung im 6. Semester empfohlen
-
Spezialisierung Angewandte Informatik (
0.0h VO, VC, KS, UE / 6.0 ECTS)
-
Subject: Spezialisierung Angewandte Informatik
(Compulsory elective)
- Master's degree programme Mathematics
(SKZ: 401, Version: 18W.1)
-
Subject: Informatics
(Compulsory elective)
-
8.4 Uncertain Knowledge: Reasoning and Learning (
2.0h VC / 4.0 ECTS)
- 621.064 Introduction to Artificial Intelligence 2 - Group A (2.0h VC / 4.0 ECTS)
-
8.4 Uncertain Knowledge: Reasoning and Learning (
2.0h VC / 4.0 ECTS)
-
Subject: Informatics
(Compulsory elective)
- Bachelor's degree programme Robotics and Artificial Intelligence
(SKZ: 295, Version: 22W.1)
-
Subject: Artificial Intelligence
(Compulsory subject)
-
4.2 Introduction to Artificial Intelligence II (
2.0h VC / 3.0 ECTS)
- 621.064 Introduction to Artificial Intelligence 2 - Group A (2.0h VC / 3.0 ECTS)
-
4.2 Introduction to Artificial Intelligence II (
2.0h VC / 3.0 ECTS)
-
Subject: Artificial Intelligence
(Compulsory subject)
Equivalent courses for counting the examination attempts
-
Wintersemester 2024/25
- 621.064 VC Introduction to Artificial Intelligence 2 (2.0h / 3.0ECTS)
-
Sommersemester 2024
- 621.066 VC Introduction to Artificial Intelligence 2 - Group B (2.0h / 3.0ECTS)
-
Wintersemester 2023/24
- 621.062 VC Introduction to Artificial Intelligence 2 (2.0h / 3.0ECTS)
-
Sommersemester 2023
- 621.062 VC Einführung in die Artificial Intelligence II (2.0h / 3.0ECTS)
-
Wintersemester 2022/23
- 621.062 VC Einführung in die Artificial Intelligence II (2.0h / 3.0ECTS)
-
Sommersemester 2022
- 621.062 VC Einführung in die Artificial Intelligence II (2.0h / 3.0ECTS)
-
Wintersemester 2021/22
- 621.062 VC Einführung in die Artificial Intelligence II (2.0h / 3.0ECTS)
-
Sommersemester 2021
- 621.062 VC Einführung in die Artificial Intelligence II (2.0h / 3.0ECTS)
-
Wintersemester 2020/21
- 621.062 VC Einführung in die Artificial Intelligence II (2.0h / 3.0ECTS)
-
Sommersemester 2020
- 621.062 VC Einführung in die Artificial Intelligence II (2.0h / 3.0ECTS)
-
Wintersemester 2019/20
- 621.062 VC Einführung in die Artificial Intelligence II (2.0h / 3.0ECTS)