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 WS 2020/1 (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 | ||
|---|---|---|
| WS 2020/1 | 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
- Task environments and the structure of intelligent agents.
- Solving problems by searching: breadth-first search, uniform-cost search, depth-first search, depth-limited search, iterative deepening search, greedy best-first search, A* search.
- Constraint satisfaction problems: defining constraint satisfaction problems, backtracking search for constraint satisfaction problems, heuristics for backtracking search, interleaving search and inference, the structure of constraint satisfaction problems.
- Logical agents: propositional logic, propositional theorem proving, syntax and semantics of first-order logic, using first-order logic, knowledge engineering in first-order logic, reducing first-order inference to propositional inference, unification and lifting, forward chaining, backward chaining, resolution.
- Bayesian networks: acting under uncertainty, basics of probability theory, Bayesian networks, inference in Bayesian networks, approximate inference in Bayesian networks.
- Hidden Markov models: time and uncertainty, inference in hidden Markov models (filtering, prediction, smoothing, most likely explanation), approximate inference in hidden Markov models.
- Rational decisions: introduction to utility theory, utility functions, decision networks, the value of information, Markov decision processes, value iteration, policy iteration, partially observable Markov decision processes.
- Learning: types of learning, supervised learning, learning decision trees.
- Introduction to robotics: robot hardware, robotic perception, path planning, planning uncertain movements, control of movements, robotic software architectures, application domains.
- Solving problems by searching: breadth-first search, uniform-cost search, depth-first search, depth-limited search, iterative deepening search, greedy best-first search, A* search.
- Constraint satisfaction problems: defining constraint satisfaction problems, backtracking search for constraint satisfaction problems, heuristics for backtracking search, interleaving search and inference, the structure of constraint satisfaction problems.
- Logical agents: propositional logic, propositional theorem proving, syntax and semantics of first-order logic, using first-order logic, knowledge engineering in first-order logic, reducing first-order inference to propositional inference, unification and lifting, forward chaining, backward chaining, resolution.
- Bayesian networks: acting under uncertainty, basics of probability theory, Bayesian networks, inference in Bayesian networks, approximate inference in Bayesian networks.
- Hidden Markov models: time and uncertainty, inference in hidden Markov models (filtering, prediction, smoothing, most likely explanation), approximate inference in hidden Markov models.
- Rational decisions: introduction to utility theory, utility functions, decision networks, the value of information, Markov decision processes, value iteration, policy iteration, partially observable Markov decision processes.
- Learning: types of learning, supervised learning, learning decision trees.
- Introduction to robotics: robot hardware, robotic perception, path planning, planning uncertain movements, control of movements, robotic software architectures, application domains.
Learning Outcome
After attending the module, you are able to create artificial intelligence on a basic level using search techniques, logics, probability theory and decision theory. Your learned abilities will be the foundation for more advanced topics in artificial intelligence. In particular, you will acquire the following skills:
- You can analyze problems of artificial intelligence and judge how difficult it is to solve them.
- You can recall the basic concepts of intelligent agents and know possible task environments.
- You can formalize, apply, and understand search problems.
- You understand the difference between constraint satisfaction and classical search problems as well as apply and evaluate various constraint satisfaction approaches.
- You can critically assess the advantages and disadvantages of logics in artificial intelligence.
- You can formalize problems using propositional and first-order logic.
- You can apply automatic reasoning techniques in propositional and first-order logic.
- You understand the advantages and disadvantages of probabilistic and logic-based reasoning.
- You can apply and critically asses methods for probabilistic reasoning with Bayesian networks and Hidden Markov Models.
- You understand and know how to compute rational decisions.
- You have a basic understanding on how a machine learns.
- You know the basic areas and concepts in robotics.
- You can analyze problems of artificial intelligence and judge how difficult it is to solve them.
- You can recall the basic concepts of intelligent agents and know possible task environments.
- You can formalize, apply, and understand search problems.
- You understand the difference between constraint satisfaction and classical search problems as well as apply and evaluate various constraint satisfaction approaches.
- You can critically assess the advantages and disadvantages of logics in artificial intelligence.
- You can formalize problems using propositional and first-order logic.
- You can apply automatic reasoning techniques in propositional and first-order logic.
- You understand the advantages and disadvantages of probabilistic and logic-based reasoning.
- You can apply and critically asses methods for probabilistic reasoning with Bayesian networks and Hidden Markov Models.
- You understand and know how to compute rational decisions.
- You have a basic understanding on how a machine learns.
- You know the basic areas and concepts in robotics.
Preconditions
IN0007 Fundamentals of Algorithms and Data Structures
IN0015 Discrete Struktures
IN0018 Discrete Probability Theory
IN0015 Discrete Struktures
IN0018 Discrete Probability Theory
Courses, Learning and Teaching Methods and Literature
Courses and Schedule
WS 2022/3
WS 2021/2
WS 2020/1
WS 2019/20
WS 2018/9
WS 2017/8
WS 2016/7
WS 2015/6
WS 2014/5
WS 2013/4
WS 2012/3
| Type | SWS | Title | Lecturer(s) | Dates | Links |
|---|---|---|---|---|---|
| VU | 4 | Techniques in Artificial Intelligence (IN2062) |
Wed, 14:00–16:00, MI HS1 Fri, 12:00–14:00, Interims I 101 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. 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. Students should ideally have tried to solve the problems before they attend the exercise. To encourage more participation, you are regularly asked questions or encouraged to participate via the software Tweedback. As an incentive to create artificial intelligence on your own, we provide programming challenges.
Media
Slides, blackboard, exercise sheets
Literature
- P. Norvig and S. Russell: Artificial Intelligence: A Modern Approach, Prentice Hall, 3rd edition. (English version)
- P. Norvig and S. Russell: Künstliche Intelligenz: Ein moderner Ansatz, Pearson Studium, 3. Auflage. (German version)
- W. Ertel: Grundkurs Künstliche Intelligenz: Eine praxisorientierte Einführung, Springer, 3. Auflage. P. Z öller-Greer: Künstliche Intelligenz: Grundlagen und Anwendungen, composia, 2. Auflage.
- D. L. Poole and A. K. Mackworth: Artificial Intelligence: Foundations of Computational Agents, Cambridge University Press.
- P. C. Jackson Jr: Introduction to Artificial Intelligence, Dover Publications.
- P. Norvig and S. Russell: Künstliche Intelligenz: Ein moderner Ansatz, Pearson Studium, 3. Auflage. (German version)
- W. Ertel: Grundkurs Künstliche Intelligenz: Eine praxisorientierte Einführung, Springer, 3. Auflage. P. Z öller-Greer: Künstliche Intelligenz: Grundlagen und Anwendungen, composia, 2. Auflage.
- D. L. Poole and A. K. Mackworth: Artificial Intelligence: Foundations of Computational Agents, Cambridge University Press.
- P. C. Jackson Jr: Introduction to Artificial Intelligence, Dover Publications.
Module Exam
Description of exams and course work
Written exam of 90 minutes at the end of the semester. 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 will cover most of the learned material and are typically shorter than the problems solved in the exercise, but similar in difficulty.
Exam Repetition
The exam may be repeated at the end of the semester.