COURSE SYLLABUS

ARTIFICIAL NEURAL NETWORKS

1	Course Title:	ARTIFICIAL NEURAL NETWORKS
2	Course Code:	EEM4420
3	Type of Course:	Optional
4	Level of Course:	First Cycle
5	Year of Study:	4
6	Semester:	8
7	ECTS Credits Allocated:	4
8	Theoretical (hour/week):	3
9	Practice (hour/week) :	0
10	Laboratory (hour/week) :	0
11	Prerequisites:	-
12	Recommended optional programme components:	None
13	Language:	Turkish
14	Mode of Delivery:	Face to face
15	Course Coordinator:	Doç. Dr. NEYİR ÖZCAN SEMERCİ
16	Course Lecturers:	-
17	Contactinformation of the Course Coordinator:	E-posta:neyir@uludag.edu.tr Tel: (224) 294 06 50 Adres: Elektronik Mühendisliği Bölümü 5. Kat, No:540
18	Website:
19	Objective of the Course:	The aim of this course is teaching sufficient theorical and practical knowledge about artificial neural networks.
20	Contribution of the Course to Professional Development	Gain the sufficient theorical and practical knowledge about artificial neural networks.

Learning Outcomes:

1	To be able to model and solve problems with artificial neural networks using toerical and practical knowledge.;
2	Gain the ability to identify, model, and solve complex engineering problems to select and apply appropriate analysis and modelling methods for artificial neural network problems.;
3	Acquiring the ability to design partly or fully with artificial neural networks for a complex system, process meeting specific requirements under realistic constraints and conditions.;
4	To be able to develop, select, and use modern techniques and tools efficiently using information technologies for artificial neural network applications.;
5	Gain the ability to design and conduct complex experiments and to collect, analyze and interpret data for artificial neural network engineering problems.;

22	Course Content:

Week	Theoretical	Practical
1	Artifical Inteligence and Artificial Neural Networks
2	Realizing Artificial Neural Networks.
3	Realizing Artificial Neural Networks: McCulloch-Pitts Model,
4	Activation functions
5	Models Artificial Neural Networks: Feedforward Neural networks, feedback neural networks
6	Learning for Artificial Neural Network: Supervised, Unsupervised, Reinforcement Learning
7	Neural Network Learning Rules: Hebbian Learning Rule, Perceptron Learning Rule, Delta Learning Rule
8	Neural Network Learning Rules: Widrow-Hoff Learning Rule, Correlation Learning Rule, Winner-Take-All Learning Rule, Outstar Learning Rule
9	Multilayer Feedforward Networks, XOR problem
10	Backpropogation Algorithm
11	Evaluation of network performance in artificial neural networks
12	Artificial Neural Network Models: LVQ Model, Adaptive Resonance Theory (Art)
13	Gradient-Type Hopfield Neural Networks and Realization using electrical components
14	CNNs, Kohen-Grossberg, Cognitron networks

23	Textbooks, References and/or Other Materials:	1. M. Jacek Zurada, , Introduction to Artificial Neural Systems, West Publishing Company, 1992, 2. S. Haykin, Neural Networks: A Comprehensive Foundation (2nd Edition), Prentice-Hall, 1998 3. L.O. Chua, T. Roska, Cellular Neural Networks and Visual Computing, Foundations and Applications, Cambridge University Press, 2002. 4. Ç. Elmas, Yapay Sinir Ağları, Seçkin Yayınevi,.2003. 5. Ö. Efe, O. Kaynak, Yapay Sinir Ağları ve Uygulamaları, Boğaziçi Ünv., 2000. 6. A. Babaev, Bulanık Mantık ve Uygulamaları, Uludağ Ünv., 1998.
24	Assesment

TERM LEARNING ACTIVITIES	NUMBER	PERCENT
Midterm Exam	1	40
Quiz	0	0
Homeworks, Performances	0	0
Final Exam	1	60
Total	2	100
Contribution of Term (Year) Learning Activities to Success Grade		40
Contribution of Final Exam to Success Grade		60
Total		100
Measurement and Evaluation Techniques Used in the Course	Measurement and evaluation is carried out according to the priciples of Bursa Uludag University Associate and Undergraduate Education Regulation.
Information	The relative evaluation system is applied. 1 Midterm and 1 Final exams are held.

ECTS / WORK LOAD TABLE

CONTRIBUTION OF LEARNING OUTCOMES TO PROGRAMME QUALIFICATIONS

LO: Learning Objectives

PQ: Program Qualifications

Contribution Level:

1 Very Low

2 Low

3 Medium

4 High

5 Very High