INTERNATIONAL BURCH UNIVERSITY
Faculty of Engineering and Natural Sciences
Department of Genetics and Bioengineering
20172018
SYLLABUS 
Code 
Name 
Level 
Year 
Semester 
GBE 321 
Intelligent Systems 
Undergraduate 
3 
Spring 
Status 
Number of ECTS Credits 
Class Hours Per Week 
Total Hours Per Semester 
Language 
Area Elective 
5 
2 + 2 
120 

This course will introduce students to the principles of fuzzy logic systems and artificial neural network systems. The focuses are on using these methods for solving different problems in Bioengineering. Topic include neural networks arhitectures and fuzzy systems, learning algorithms and application, Matlab software  Neural Network Toolbox and Fuzzy Logic Toolbox. 
COURSE OBJECTIVE 
The aim of this course is to provide students with an understanding of the fundamental theory of neural networks, fuzzy logic systems, eulebased systems and expert system development. 
COURSE CONTENT 
 Introduction: Characteristics of ANN and Fuzzy Systems, Biological Neuron, Artificial Neuron, Artificial Neural Networks, Phases in ANN Operation, Network Classification;
 Unsupervised Learning: Hebbian Learning, Competitive Learning & Boltzmann Learning
 Supervised Learning (ErrorCorrection learning) and Reinforcement Learning;
 Perceptrons and Multilayer Perceptrons
 Neural network Applications;
 Fuzzy Sets and Operations
 Fuzzy Representation of Structured Knowledge
 Fuzzy System application and Fuzzy sense in ANN
 Expert systems based on fuzzy logic and artificial neural network

LABORATORY/PRACTICE PLAN 
 Introduction: Characteristics of ANN and Fuzzy Systems, Biological Neuron, Artificial Neuron, Artificial Neural Networks, Phases in ANN Operation, Network Classification;
 Unsupervised Learning: Hebbian Learning, Competitive Learning & Boltzmann Learning
 Supervised Learning (ErrorCorrection learning) and Reinforcement Learning;
 Perceptrons and Multilayer Perceptrons
 Neural network Applications;
 Fuzzy Sets and Operations
 Fuzzy Representation of Structured Knowledge
 Fuzzy System application and Fuzzy sense in ANN
 Expert systems based on fuzzy logic and artificial neural network

Description 
 Interactive Lectures
 Practical Sessions
 Excersises
 Presentation
 Discussions and group work
 Assignments
 Guest instructor

Learning outcomes 
 Designing and applying fuzzy logic system to solve engineering control problems where only expert linguistic knowledge is available,
 Designing and applying artificial neural network for solving problems
 Different aspects and methods of applying fuzzy logic system and artificial neural network in Bioengineering
 The difference between the classical algorithmic way of solving the problems and the corresponding learning procedures of artificial neural networks
 Technical possibilities, the advantages and the limitations of the fuzzy logic systems, artificial nerual network systems
 Usage of available software tools such as Matlab Neural Network Toolbox
 Developing Intelligent Expert Systems for solving complex problems in the Bioengineering area

TEXTBOOK(S) 
 S.J. Russell and P. Norvig. Artificial Intelligence: A Modern Approach (3rd edition), PrenticeHall, 2010.
 Machine Learning: A Probabilistic Perspective, Kevin R Murphy, MIT Press, 2012
 Pattern Recognition and Machine Learning Christopher M. Bishop, Springer, 2006.
 Fuzzy Logic and Mathematics Historical Perspective Radim Belohlavek, Joseph W. auben, and George J. Klir, Oxford University Press, 2017

ECTS (Allocated based on student) WORKLOAD 
Lecture (14 weeks x Lecture hours per week)  14  2  28  Laboratory / Practice (14 weeks x Laboratory/Practice hours per week)  14  2  28  Midterm Examination (1 week)  1  2  2  Final Examination(1 week)  1  2  2  Preparation for Midterm Examination  1  14  14  Preparation for Final Examination  1  14  14  Assignment / Homework/ Project  1  14  14  Seminar / Presentation  1  18  18 

