ACADEMICS
Course Details

ELE785 - Neural Networks

2022-2023 Fall term information
The course is not open this term
ELE785 - Neural Networks
Program Theoretýcal hours Practical hours Local credit ECTS credit
PhD 3 0 3 10
Obligation : Elective
Prerequisite courses : -
Concurrent courses : -
Delivery modes : Face-to-Face
Learning and teaching strategies : Lecture, Question and Answer, Drill and Practice, Case Study, Problem Solving
Course objective : The course objective is to study on comprehension of the learning paradigms and their network realizations together with introducing well known neural network topologies and their associated learning algorithms. The course would more emphasize the signal processing aspects of neural network tools in engineering applications.
Learning outcomes : A student completing the course successfully will know some basic and pioneering efforts in learning and classification problems, Study knowledge representations and basic learning units, Have the fundamental optimisation theory and links to learning paradigms, Compare the standarts methods and Neural networks approaches in the scope of classification and learning, Learn important classes in Neural Networks in terms of supervised vs unsupervised and dynamic vs static requirements of engineering problems, Have the fundamental knowledge to follow and understand advanced up-to-date neural network algorithms. Efficiently use relevant computer programming tools for developing problem solutions.
Course content : 1. Introduction to neural networks, 2. Fundamental concepts ? neuron models, Mc Culloch Pitts model, Rosenblatt?s perceptron, learning, 3. Regression and optimization: Least square estimation, recursive least square estimation, derivative based optimization, 4. Single layer perceptrons, 5. Multilayer perceptrons, 6. Self organizing systems: Hebbian learning, Kohonen map, 7. Dynamic networks: Time delay neural networks, recurrent neural networks 8. Radial basis networks
References : Haykin, S., Neural Networks, A comprehensive Foundation, Prentice Hall, 2nd ed., 1999.; ; Jang, J.S.R., Sun T.S., Mizutani, E., Neuro-Fuzzy and Soft Computing, Prentice Hall, 1997.; ; Lau, C., edt., Neural Networks, Theoretical Foundations and Analysis, IEEE Press, 1992.; ; Cichocki, A., Unbehauen, R. ,Neural Networks for Optimization and Signal Processing, Wiley,1993. ; ; Shalkoff, R.J., ?Artificial Neural Networks?, Mc Graw Hill, 1997.; ; Haykin. S., ? Adaptive Filter Theory?, Prentice Hall, 1996.
Course Outline Weekly
Weeks Topics
1 Introduction to neural networks
2 Fundamental concepts ? neuron models, Mc Culloch Pitts model
3 Fundamental concepts ? Knowledge representation, Rosenblatt?s perceptron, learning paradigms
4 Regression and optimization: least square estimation, recursive least square estimation,
5 Regression and optimization: derivative based optimization
6 Single layer perceptrons
7 Multilayer perceptrons: Backpropagation algorithm
8 Multilayer perceptrons: Programming considerations, applications
9 Midterm Exam
10 Self orginizing systems: Hebbian lerning, Kohonen map
11 Dynamic networks: time delay neural networks
12 Dynamic networks: recurrent neural networks
13 Radial basis networks
14 Engineering applications and comparisons
15 Final exam
16 Final exam
Assessment Methods
Course activities Number Percentage
Attendance 0 0
Laboratory 0 0
Application 0 0
Field activities 0 0
Specific practical training 0 0
Assignments 3 45
Presentation 0 0
Project 0 0
Seminar 0 0
Quiz 0 0
Midterms 1 15
Final exam 1 40
Total 100
Percentage of semester activities contributing grade success 60
Percentage of final exam contributing grade success 40
Total 100
Workload and ECTS Calculation
Course activities Number Duration (hours) Total workload
Course Duration 14 3 42
Laboratory 0 0 0
Application 0 0 0
Specific practical training 0 0 0
Field activities 0 0 0
Study Hours Out of Class (Preliminary work, reinforcement, etc.) 13 8 104
Presentation / Seminar Preparation 0 0 0
Project 0 0 0
Homework assignment 3 25 75
Quiz 0 0 0
Midterms (Study duration) 1 15 15
Final Exam (Study duration) 1 25 25
Total workload 32 76 261
Matrix Of The Course Learning Outcomes Versus Program Outcomes
Key learning outcomes Contribution level
1 2 3 4 5
1. Has highest level of knowledge in certain areas of Electrical and Electronics Engineering.
2. Has knowledge, skills and and competence to develop novel approaches in science and technology.
3. Follows the scientific literature, and the developments in his/her field, critically analyze, synthesize, interpret and apply them effectively in his/her research.
4. Can independently carry out all stages of a novel research project.
5. Designs, plans and manages novel research projects; can lead multidisiplinary projects.
6. Contributes to the science and technology literature.
7. Can present his/her ideas and works in written and oral forms effectively; in Turkish or English.
8. Is aware of his/her social responsibilities, evaluates scientific and technological developments with impartiality and ethical responsibility and disseminates them.
1: Lowest, 2: Low, 3: Average, 4: High, 5: Highest
General Information | Course & Exam Schedules | Real-time Course & Classroom Status
Undergraduate Curriculum | Open Courses, Sections and Supervisors | Weekly Course Schedule | Examination Schedules | Information for Registration | Prerequisite and Concurrent Courses | Legal Info and Documents for Internship | Academic Advisors for Undergraduate Program | Information for ELE 401-402 Graduation Project | Virtual Exhibitions of Graduation Projects | Program Educational Objectives & Student Outcomes | ECTS Course Catalog | HU Registrar's Office
Graduate Curriculum | Open Courses and Supervisors | Weekly Course Schedule | Final Examinations Schedule | Schedule of Graduate Thesis Defences and Seminars | Information for Registration | ECTS Course Catalog - Master's Degree | ECTS Course Catalog - PhD Degree | HU Graduate School of Science and Engineering