INTERNATIONAL BURCH UNIVERSITY
Faculty of Engineering and Natural Sciences
Department of Genetics and Bioengineering
2017-2018

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

Instructor Assistant Coordinator
Almir Badnjević, Assist. Prof. Dr. Almir Badnjević Almir Badnjević, Assist. Prof. Dr.
[email protected] [email protected] no email

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, eule-based systems and expert system development.

COURSE CONTENT
Week
Topic
  1. Introduction: Characteristics of ANN and Fuzzy Systems, Biological Neuron, Artificial Neuron, Artificial Neural Networks, Phases in ANN Operation, Network Classification;
  2. Unsupervised Learning: Hebbian Learning, Competitive Learning & Boltzmann Learning
  3. Supervised Learning (Error-Correction learning) and Reinforcement Learning;
  4. Perceptrons and Multilayer Perceptrons
  5. Neural network Applications;
  6. Fuzzy Sets and Operations
  7. Fuzzy Representation of Structured Knowledge
  8. Fuzzy System application and Fuzzy sense in ANN
  9. Expert systems based on fuzzy logic and artificial neural network

LABORATORY/PRACTICE PLAN
Week
Topic
  1. Introduction: Characteristics of ANN and Fuzzy Systems, Biological Neuron, Artificial Neuron, Artificial Neural Networks, Phases in ANN Operation, Network Classification;
  2. Unsupervised Learning: Hebbian Learning, Competitive Learning & Boltzmann Learning
  3. Supervised Learning (Error-Correction learning) and Reinforcement Learning;
  4. Perceptrons and Multilayer Perceptrons
  5. Neural network Applications;
  6. Fuzzy Sets and Operations
  7. Fuzzy Representation of Structured Knowledge
  8. Fuzzy System application and Fuzzy sense in ANN
  9. Expert systems based on fuzzy logic and artificial neural network

TEACHING/ASSESSMENT
Description
  • Interactive Lectures
  • Practical Sessions
  • Excersises
  • Presentation
  • Discussions and group work
  • Assignments
  • Guest instructor
Description (%)
Method Quantity Percentage (%)
Midterm Exam(s)120
Total: 20
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), Prentice-Hall, 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
Activities Quantity Duration (Hour) Total Work Load
Lecture (14 weeks x Lecture hours per week)14228
Laboratory / Practice (14 weeks x Laboratory/Practice hours per week)14228
Midterm Examination (1 week)122
Final Examination(1 week)122
Preparation for Midterm Examination11414
Preparation for Final Examination11414
Assignment / Homework/ Project11414
Seminar / Presentation11818
Total Workload: 120
ECTS Credit (Total workload/25): 5