Computational Intelligence
PDF Course Catalog Deutsche Version: CI
Version: 1 | Last Change: 25.09.2019 18:14 | Draft: 0 | Status: vom verantwortlichen Dozent freigegeben
Long name | Computational Intelligence |
---|---|
Approving CModule | CI_MaTIN |
Responsible |
Prof. Dr. Rainer Bartz
Professor Fakultät IME |
Valid from | summer semester 2021 |
Level | Master |
Semester in the year | summer semester |
Duration | Semester |
Hours in self-study | 78 |
ECTS | 5 |
Professors |
Prof. Dr. Rainer Bartz
Professor Fakultät IME |
Requirements | vector functions, gradient |
Language | German, English if necessary |
Separate final exam | Yes |
Domschke W., Drexl A.; Einführung in Operations Research; Springer |
Zell, A.: Simulation Neuronaler Netze; Oldenbourg |
Nauck, D. et al.: Neuronale Netze und Fuzzy-Systeme; Vieweg |
Eiben, A.E., Smith, J.E.: Introduction to Evolutionary Computing; Springer |
Gerdes, I. et al.: Evolutionäre Algorithmen; Vieweg |
Grosse et al.: Taschenbuch der praktischen Regelungstechnik, Fachbuchverlag Leipzig |
Details | written exam |
---|---|
Minimum standard | roughly 50% |
Exam Type | EN Klausur |
Goal type | Description |
---|---|
Knowledge | Optimization strategies - classification of problems - gradient algorithms - simplex algorithm - multiobjective optimization and Pareto approach |
Knowledge | Artificial neural networks - artificial neurons - neural network structures - training algorithms |
Knowledge | Fuzzy logic - fuzzification - inference - defuzzification |
Knowledge | Evolutionary algorithms - genome representations - selection mechanisms - recombination operators - mutation operators |
Skills | The students acquire fundamental knowledge on theory and applications of computational intelligence |
Skills | The students know about typical classes of optimization tasks and how to map a specific problem to those classes |
Skills | They know the simplex algorithm and can transform problems into the standard form to find the solutions |
Skills | The students can classify artificial neural networks and determine their applicability for specific tasks |
Skills | They can vary the parameters of neural networks and rate their impact on the results |
Skills | They can classify training algorithms and understand the backpropagation algorithm |
Skills | They know about the fuzzy logic approach, can apply it to specific problems and justify the resulting system behavior |
Skills | The students know how evolutionary algorithms work and can distinguish the variants |
Skills | They can transform a problem specification into a representation appropriate for an evolutionary algorithm |
Skills | They can rate selection strategies and define suitable algorithms |
Skills | The students can solve linear problems with the use of the simplex algorithm |
Skills | They can apply artificial neural networks to solve problems of modeling and classification |
Skills | They can define fuzzy logic systems to solve imprecise and vague tasks |
Skills | They can solve difficult problems heuristically using evolutionary algorithms |
Type | Attendance (h/Wk.) |
---|---|
Lecture | 2 |
Exercises (whole course) | 1 |
Exercises (shared course) | 0 |
Tutorial (voluntary) | 0 |
none |
Accompanying material |
Compendium with course contents (in engl. language) Exercises and solutions (in engl. language) |
---|---|
Separate exam | No |
Goal type | Description |
---|---|
Knowledge | Application of artificial neural networks to a classification task |
Knowledge | Variation and multiobjective optimization of neural network parameters |
Knowledge | Fuzzy-based closed loop control of a system with two inputs |
Skills | The students are familiar with tools supporting computational intelligence |
Skills | The students can vary system parameters, perform test series, and evaluate, present and discuss the results |
Skills | The students are able to understand, present, analyze and discuss scientific publications |
Skills | The students are able to solve problems in small teams |
Skills | They can tackle optimization tasks in a structured and systematic way |
Skills | They can rate the behavior of a system with regard to objectives and study and improve the behavior through parameter variations |
Skills | They are able to cope with international scientific publications, understanding, presenting and discussing them in their context |
Type | Attendance (h/Wk.) |
---|---|
Practical training | 1 |
Tutorial (voluntary) | 0 |
none |
Accompanying material | Specification of the lab tasks (in engl. language), Electronic documentation of the tools to be used |
---|---|
Separate exam | No |
© 2022 Technische Hochschule Köln