Techniques in Artificial Intelligence
Module IN2062
This module handbook serves to describe contents, learning outcome, methods and examination type as well as linking to current dates for courses and module examination in the respective sections.
Module version of SS 2015 (current)
There are historic module descriptions of this module. A module description is valid until replaced by a newer one.
Whether the module’s courses are offered during a specific semester is listed in the section Courses, Learning and Teaching Methods and Literature below.
| available module versions | |
|---|---|
| SS 2015 | WS 2011/2 |
Basic Information
IN2062 is a semester module in German or English language at Bachelor’s level and Master’s level which is offered in winter semester.
This Module is included in the following catalogues within the study programs in physics.
- Focus Area Imaging in M.Sc. Biomedical Engineering and Medical Physics
- Catalogue of non-physics elective courses
| Total workload | Contact hours | Credits (ECTS) |
|---|---|---|
| 150 h | 60 h | 5 CP |
Content, Learning Outcome and Preconditions
Content
The course gives an overview of application areas and techniques in Artificial Intelligence. The course introduces the principles and techniques of Artificial Intelligence based on the textbook of Russell and Norvig (see below). The course covers the following topics:
- design principles and specification mechanisms for rational agents;
- problem solving using heuristic search: heuristic search techniques, optimizing search;
- problem solving using knowledge-based techniques: logic and inference techniques; reasoning about space and time; representation of ontologies; representation and reasoniong in the common sense world;
- problem solving using uncertain knowledge and information: basic concepts of probability and decision theory; Bayesian Networks; planning with Markov decision problems;
- action planning: automatic generation of partially ordered action plans; planning and execution;
- machine learning: learning decision trees; inductive learning; probably approximately correct learning; reinforcement learning.
- design principles and specification mechanisms for rational agents;
- problem solving using heuristic search: heuristic search techniques, optimizing search;
- problem solving using knowledge-based techniques: logic and inference techniques; reasoning about space and time; representation of ontologies; representation and reasoniong in the common sense world;
- problem solving using uncertain knowledge and information: basic concepts of probability and decision theory; Bayesian Networks; planning with Markov decision problems;
- action planning: automatic generation of partially ordered action plans; planning and execution;
- machine learning: learning decision trees; inductive learning; probably approximately correct learning; reinforcement learning.
Learning Outcome
The participants will attain capabilities to solve complex problems using fundamental methods and techniques of artificial intelligence. The techniques include agent-based problem solving, problem solving through (heuristic) search, the representation of knowledge, reasoning mechanisms, problem solving under uncertainty, action planning and machine learning.
Examples are search algorithms, methods of logical inference, as well as computation of state probabilities of Bayesian networks and hidden Markov models.
Examples are search algorithms, methods of logical inference, as well as computation of state probabilities of Bayesian networks and hidden Markov models.
Preconditions
IN0007 Fundamentals of Algorithms and Data Structures, IN0015 Discrete Struktures
Courses, Learning and Teaching Methods and Literature
Courses and Schedule
| Type | SWS | Title | Lecturer(s) | Dates | Links |
|---|---|---|---|---|---|
| VI | 4 | Techniques in Artificial Intelligence (IN2062) | Althoff, M. Kochdumper, N. Koschi, M. Miller, C. |
Fri, 13:00–14:30, MW 2001 Wed, 14:00–16:00, MI HS1 Wed, 11:00–12:00, MI 03.07.023 and singular or moved dates |
eLearning documents |
Learning and Teaching Methods
The module consists of a lecture and exercise classes. The content of the lecture is presented via slides, which are completed during the lecture using the blackboard. Also, the learning progress is checked during the lecture using the survey tool Tweedback. Students are encouraged to additionally study the relevant literature. In the exercise classes, the learned content is applied to practical examples to consolidate the content of the lecture.
Media
Slides, assignment sheets
Literature
Stuart Russel and Peter Norvig: Artificial Intelligence - A Modern Approach, Prentice Hall
Module Exam
Description of exams and course work
The duration of the written exam is 90 minutes. In the written exam students should prove to be able to identify a given problem and find solutions within limited time.
A collection of formulas and tables required to solve the given problems is provided. Students are only allowed to bring pens and a calculator (non-progammable). The questions require to solve problems mathematically and to answer questions in natural language.
A collection of formulas and tables required to solve the given problems is provided. Students are only allowed to bring pens and a calculator (non-progammable). The questions require to solve problems mathematically and to answer questions in natural language.
Exam Repetition
The exam may be repeated at the end of the semester.
Current exam dates
Currently TUMonline lists the following exam dates. In addition to the general information above please refer to the current information given during the course.
| Title | |||
|---|---|---|---|
| Time | Location | Info | Registration |
| Techniques in Artificial Intelligence | |||
| Wed, 2021-03-31, 14:15 till 15:45 | elektronische Übungsleistung https://www.tum.de/die-tum/aktuelles/coronavirus/corona-lehre-pruefungen/ | till 2021-03-22 (cancelation of registration till 2021-03-24) | |