EventoWeb
Zürcher Hochschule für Angewandte Wissenschaften
[
German (Switzerland)
German (Switzerland)
] [
English
English
]
Not registered
[home]
[Login]
[Print]
Navigation
Kontakt zu Service Desk
Online-Dokumentation
Allgemeiner Zugriff
Module suchen
t.BA.IT.KI1.16HS (Artificial Intelligence 1)
Module: Artificial Intelligence 1
This information was generated on: 26 April 2024
No.
t.BA.IT.KI1.16HS
Title
Artificial Intelligence 1
Organised by
T CAI
Credits
4
Description
Version: 3.0 start 01 August 2017
Module coordinator:
Thilo Stadelmann (stdm), Mark Cieliebak (ciel)
Learning objectives:
Objectives
Competences
Taxonomy levels
(1) You know the breadth of AI and particularly Machine Learning (ML) problem solving strategies
D
C1
...thus identify such challenges in practice
D, M
C2, C4
...and develop corresponding solutions on your own.
D, M
C3
(2) You can explain the discussed algorithms and methodologies
F
C2
...and are able to transfer it to the real world.
D, M
C3
Module contents:
What is it all about?
Computer opponents in games, fastest route in navigation devices, optimized flight schedules, decision support in hospitals, design of pharmaceutical proteins to fight cancer – the foundation of all these fascinating application is "Artificial Intelligence" (AI).
Why is it relevant?
Since the 1960s, AI is about developing solutions for complex problems that could formerly only be solved by humans. AI is a classical subdiscipline of computer science. Its methods are so universally used that our text book for this course is among the 25 most-cited scientific publications on Citeseer!
Who should attend?
This is a very much practice-oriented course on selected foundations of AI and Machine Learning (ML), aiming at hands-on problem solving competency for everyday software challenges. It is geared towards everyone who is curious for smart software and is especially relevant for software engineers, would-be data scientists and as a foundation for further interdisciplinary studies in areas like information engineering, speech processing, computer vision or robotics.
This is part 1 of a 2-semester course.
Content
Introduction to AI: What as (artificial) intelligence? -> Methods: the concept of an intelligent agent
-> Practice: Introduction to Python
Search: How to find suitable sequences of actions to reach a complex goal?
-> Methods: e.g. uninformed & heuristic search, the Minimax algorithm, constraint satisfaction problems
-> Practice: AI for games (e.g., 2048)
Planning: How to represent knowledge that facilitates reasoning in an intelligent way?
How to describe a problem with rules and find a solution via logical inference? Is this also possible with "Big Data"?
-> Mehtods: e.g. logic as a basis for knowledge engineering and reasoning
-> Practice: AI for spies (e.g. dragnet investigation using Datalog)
Supervised Machine Learning: What is (automated) learning? How to learn from examples?
-> Methods: e.g. from decision trees to ensembles and state of the art methods
-> Practice: AI for data miners (e.g the ML process for data analysis)
The labs ("practice" above) are used by the students to explore on their own, based on the lectures, in ca. one experiment per lecture block solutions to challenges from the practice of a developer of smart software.
Literature:
Russel, Norvig: „Artificial Intelligence – A Modern Approach“, 3rd Edition, Pearson, 2010. (Also in German)
Material of this course (e.g., slides)
Supplementary literature:
Scientific publications
Prerequisites:
Successfully completed assessment phase, affinity towards algorithms, enjoying the topic
Teaching language:
German (English is possible if wished and agreed upon)
Module structure:
Form of instruction:
Number of lessons per week:
Lecture:
2
Labs:
2
Block course:
-
Exams:
The regulation on graded class assignments is binding. However, it may be waived if a formal, written request is made by the lecturer in the first week of the semester.
Designation
Type
Form
Scope
Grade
Weighting
Graded assignments during teaching semester
Colloquium for labs
oral
within labs
max. 20 points
20%
End-of-semester exam
Written exam or oral assessment
By agreement at semester start
90 min. written exam or 30 min. oral assessment
max. 80 points
80%
Remarks:
Note
Additional available versions:
1.0 start 01 February 2017
Course: Artificial Intelligence 1 - Praktikum
No.
t.BA.IT.KI1.16HS.P
Title
Artificial Intelligence 1 - Praktikum
Note
No module description is available in the system for the cut-off date of 26 April 2024.
Course: Artificial Intelligence 1 - Vorlesung
No.
t.BA.IT.KI1.16HS.V
Title
Artificial Intelligence 1 - Vorlesung
Note
No module description is available in the system for the cut-off date of 26 April 2024.