Module also offered within study programmes:
General information:
Name:
Neural networks and fuzzy systems in engineering
Course of study:
2013/2014
Code:
RMS-1-608-s
Faculty of:
Mechanical Engineering and Robotics
Study level:
First-cycle studies
Specialty:
-
Field of study:
Mechatronics with English as instruction languagege
Semester:
6
Profile of education:
Academic (A)
Lecture language:
English
Form and type of study:
Full-time studies
Course homepage:
 
Responsible teacher:
dr inż. Czop Piotr (pczop@agh.edu.pl)
Academic teachers:
dr inż. Czop Piotr (pczop@agh.edu.pl)
Module summary

Description of learning outcomes for module
MLO code Student after module completion has the knowledge/ knows how to/is able to Connections with FLO Method of learning outcomes verification (form of completion)
Social competence
M_K001 is able to evaluate important and less important aspects (priorities) in a solving process of engineering problems with the use of neural networks or fuzzy-logic systems Engineering project,
Execution of laboratory classes
M_K002 learns and develops teamwork skills Involvement in teamwork
M_K003 improves ability to evaluate required human and hardware resources in application to solve engineering problems with neural networks and fuzzy-logic systems Engineering project
Skills
M_U001 is able to define a neural network structure required to solve a given engineering problem Execution of laboratory classes
M_U002 is able to create a multi-layer neural network with a topology adequate to solve a simple engineering task, e.g. approximation of data generated with the use of a nonlinear mathematical function. Execution of laboratory classes
M_U003 is able to develop a fuzzy-logic system allowing to conduct an inference process in order to solve a simple engineering task, e.g. taking design or maintenance decision, grouping or classifying data sets Execution of laboratory classes
Knowledge
M_W001 has a fundamental knowledge regarding neural network taxonomy, architectures and topologies. knows basic methods of learning of neural networks. Test
M_W002 has fundamental knowledge in area of fuzzy algebra and fuzzy inference methods Test
M_W003 has knowledge about adjustment and identification of parameters of neural and fuzzy logic systems and their combinations with the use of numerical optimization methods. Test
M_W004 has ability to provide research and commercial application areas of neural networks and fuzzy-logic systems taking into account their strengths and weaknesses (advantages/disadvantages) Test
FLO matrix in relation to forms of classes
MLO code Student after module completion has the knowledge/ knows how to/is able to Form of classes
Lecture
Audit. classes
Lab. classes
Project classes
Conv. seminar
Seminar classes
Pract. classes
Others
Zaj. terenowe
Zaj. warsztatowe
E-learning
Social competence
M_K001 is able to evaluate important and less important aspects (priorities) in a solving process of engineering problems with the use of neural networks or fuzzy-logic systems + - + - - - - - - - -
M_K002 learns and develops teamwork skills - - + - - - - - - - -
M_K003 improves ability to evaluate required human and hardware resources in application to solve engineering problems with neural networks and fuzzy-logic systems - - + - - - - - - - -
Skills
M_U001 is able to define a neural network structure required to solve a given engineering problem - - + - - - - - - - -
M_U002 is able to create a multi-layer neural network with a topology adequate to solve a simple engineering task, e.g. approximation of data generated with the use of a nonlinear mathematical function. - - + - - - - - - - -
M_U003 is able to develop a fuzzy-logic system allowing to conduct an inference process in order to solve a simple engineering task, e.g. taking design or maintenance decision, grouping or classifying data sets - - + - - - - - - - -
Knowledge
M_W001 has a fundamental knowledge regarding neural network taxonomy, architectures and topologies. knows basic methods of learning of neural networks. + - - - - - - - - - -
M_W002 has fundamental knowledge in area of fuzzy algebra and fuzzy inference methods + - - - - - - - - - -
M_W003 has knowledge about adjustment and identification of parameters of neural and fuzzy logic systems and their combinations with the use of numerical optimization methods. + - - - - - - - - - -
M_W004 has ability to provide research and commercial application areas of neural networks and fuzzy-logic systems taking into account their strengths and weaknesses (advantages/disadvantages) + - - - - - - - - - -
Module content
Lectures:

1. Introduction
2. Model of an artifical neuron
3. Topologies and classification of neural networks
4. Fuzz-sets theory and fuzzy inference methods
5. Classification of fuzzy-systems.
6. Neural networks and fuzzy system learning process
7. Application scope

Laboratory classes:

1. Network topologies
2. Training methods
3. Fuzzy system inference mechanism
4. Applications: time series forecasting
5. Applications: approximation and modeling of dynamic systems
6. Applications: pattern recognition

Student workload (ECTS credits balance)
Student activity form Student workload
Summary student workload 80 h
Module ECTS credits 3 ECTS
Realization of independently performed tasks 50 h
Preparation for classes 30 h
Additional information
Method of calculating the final grade:

Average from an exam and laboratory exercises (project-orientated work)

Prerequisites and additional requirements:

Ability to work with Matlab/Simulink packages
Ability to use an algorithmic approach to solve engineering problems
Knowledge about numerical methods including algorithms for minimizing the criterial function regarding the zero-order methods (searching), first-, and second order methods (first/second derivative)
Knowledge about fuzzy algebra and fuzzy-logic inference methods
Knowledge about theory of neural networks

Recommended literature and teaching resources:

1. Tadeusiewicz R.: Sieci neuronowe, Warszawa 1993
2. Tadeusiewicz R.: Odkrywanie właściwości sieci neuronowych przy użyciu programów w języku C#, Kraków 2007
3. Żurada J., Barski M., Jędruch M.: Sztuczne sieci neuronowe, Warszawa 1996
4. Fausett L., Fundamental of Neural Networks architectures, algorithms, and applications, Prentice Hall, USA 1994.
5. Osowski S., Sieci neuronowe do przetwarzania informacji, Warszawa 2006.

Scientific publications of module course instructors related to the topic of the module:

Additional scientific publications not specified

Additional information:

None