COURSE SYLLABUS

NEURAL NETWORKS AND APPLICATIONS

1	Course Title:	NEURAL NETWORKS AND APPLICATIONS
2	Course Code:	BMB3020
3	Type of Course:	Optional
4	Level of Course:	First Cycle
5	Year of Study:	3
6	Semester:	6
7	ECTS Credits Allocated:	5
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. Metin BİLGİN
16	Course Lecturers:
17	Contactinformation of the Course Coordinator:	Bilgisayar Müh. Bölüm Binası, 1. kat, oda 3 Tel.:+90 (224) 275 52 63 email: metinbilgin at uludag.edu.tr
18	Website:
19	Objective of the Course:	The goal of the course is to give the students basic knowledge about techniques based on ANN (Artificial Neural Networks) and other learning methods and practical experience of using such methods with an understanding of the role of neural networks in computer engineering, computer science and artificial intelligence.
20	Contribution of the Course to Professional Development	Engineering Science: 70%; Engineering Design: 30%

Learning Outcomes:

1	To learn basic concepts of artificial neural networks, mathematical and software background; to have ability to apply ANN to problems. To recognize the role of neural networks in computer engineering, computer science and artificial intelligence.;
2	To introduce and to learn ability to use popular ANN Tools like in Matlab. To enable to write simple ANN libraries in modern programming platforms (like Java and C#). To Develop Prediction, Estimation, Classification and Recognition Projects.;
3	To develop Intelligent Software; To recognize that how the computers learn; To design efficient ANN.;
4	To do research in state-of-the-art subjects of artificial neural area; preparing and doing presentation. To gain experience in reading and writing papers in ANN.;

22	Course Content:

Week	Theoretical	Practical
1	Why use neural networks ? Biological fondations of ANNs.
2	Application areas, typical architectures, activation functions
3	McCulloch-Pitts Neuron
4	Simple Neural Networks for Pattern Classification
5	Perceptron, Adaline, Delta Rule
6	Multilayer Perceptrons
7	Radial Based Networks
8	Gradient Descent, Backpropogation algorithms and variations
9	Gradient Descent, Backpropogation algorithms and variations
10	Learning Vector Quantization
11	Pattern Association, learning algorithms, associative networks
12	Hopfield Networks
13	Recurrent Networks
14	Application Examples

23	Textbooks, References and/or Other Materials:	1) Prof. Dr. Ercan Öztemel, 2003, “Yapay Sinir Ağları”, Papatya Yayıncılık, 238s. (Ders Kitabı) 2) Prof. Dr. Çetin Elmas, 2007, "Yapay Zeka Uygulamaları", Seçkin Yayıncılık, 425 s. 3) Haykin, Simon, 1998, “Neural Networks: A Comprehensive Foundation (2nd Edition)”, Prentice-Hall, 842p.
24	Assesment

TERM LEARNING ACTIVITIES	NUMBER	PERCENT
Midterm Exam	1	25
Quiz	0	0
Homeworks, Performances	1	25
Final Exam	1	50
Total	3	100
Contribution of Term (Year) Learning Activities to Success Grade		50
Contribution of Final Exam to Success Grade		50
Total		100
Measurement and Evaluation Techniques Used in the Course	Midterm and Final Exams
Information

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