PAÜ .:. Eğitim Öğretim Bilgi Sistemi

COURSE INFORMATION

Course Code	Course Title	L+P Hour	Semester	ECTS
CENG 511	NEURAL NETWORKS AND ENGINEERING APPLICATIONS	3 + 0	2nd Semester	7,5

COURSE DESCRIPTION

Course Level	Master's Degree
Course Type	Elective
Course Objective	Learning of Artificial Neural Network concept, improving some models via Artificial Neural Networks, providing ability for determining the optimal network model.
Course Content	Biological neurons, artificial neuron models; Neural net architectures, fully connected, layered, feed forward and modular networks; Neural learning, correlation and feedback-based weight adaptation learning; Neural network usages, classification, clustering, vector quantization, pattern recognition, function approximation, forecasting, control applications, optimization; Preprocessing, scanned image input, image compression, edge detection, segmentation; Principal component neural networks, k-means; Various Remote Sensing Applications of Artificial Neural Networks.
Prerequisites	No the prerequisite of lesson.
Corequisite	No the corequisite of lesson.

COURSE LEARNING OUTCOMES

1	Differentiates between suitable and unsuitable areas for using of Artificial Neural Networks
2	Lists various of ANNs
3	Represents different structures for ANNs
4	Represents implementation of ANNs in Matlab
5	Explains Matlab ANN toolbox

COURSE'S CONTRIBUTION TO PROGRAM

	PO 01	PO 02	PO 03	PO 04	PO 05	PO 06	PO 07	PO 08	PO 09	PO 10	PO 11	PO 12
LO 001	5	2	4	3	2
LO 002	5	2	4	3	2
LO 003	5	2	4	3	2
LO 004	5	2	4	3	2
LO 005	5	2	4	3	2
Sub Total	25	10	20	15	10
Contribution	5	2	4	3	2	0	0	0	0	0	0	0

ECTS ALLOCATED BASED ON STUDENT WORKLOAD BY THE COURSE DESCRIPTION

Activities	Quantity	Duration (Hour)	Total Work Load (Hour)
Course Duration (14 weeks/theoric+practical)	14	3	42
Hours for off-the-classroom study (Pre-study, practice)	14	5	70
Assignments	5	8	40
Mid-terms	1	15	15
Final examination	1	28	28
Total Work Load ECTS Credit of the Course			195 7,5

COURSE DETAILS

Select Year

Course Details

Course Code	Course Title	L+P Hour	Course Code	Language Of Instruction	Course Semester	Mode of Delivery
CENG 511	NEURAL NETWORKS AND ENGINEERING APPLICATIONS	3 + 0	1	Turkish	2013-2014 Fall	Face to Face

Course Coordinator	E-Mail	Phone Number	Course Location	Attendance
Prof. Dr. EMRE ÇOMAK	ecomak@pau.edu.tr		MUH A04125	%

Goals		Learning of Artificial Neural Network concept, improving some models via Artificial Neural Networks, providing ability for determining the optimal network model.
Content		Biological neurons, artificial neuron models; Neural net architectures, fully connected, layered, feed forward and modular networks; Neural learning, correlation and feedback-based weight adaptation learning; Neural network usages, classification, clustering, vector quantization, pattern recognition, function approximation, forecasting, control applications, optimization; Preprocessing, scanned image input, image compression, edge detection, segmentation; Principal component neural networks, k-means; Various Remote Sensing Applications of Artificial Neural Networks.

Topics

Weeks	Topics
1	Real and Artificial Neurons
2	Concepts of Supervised and Unsupervised Learning
3	Perceptron and Multi Layer Perceptron
4	Radial Basis Neural Networks
5	Time Delay and Recurrent Neural Networks
6	Unsupervised Neural Networks
7	Neural Networks as Associative Memories
8	Variations of Neural Networks
9	Linear Neural Network in Matlab
10	Competetive Neural Networks in Matlab
11	Feed Forward Neural Networks in Matlab
12	Regression Neural Networks in Matlab
13	Discussion and Presentation of Homeworks
14	Discussion and Presentation of Homeworks

Materials

Materials are not specified.

Resources

Course Assessment

Assesment Methods	Percentage (%)	Assesment Methods Title
Final Exam	60	Final Exam
Midterm Exam	40	Midterm Exam

L+P: Lecture and Practice
PQ: Program Learning Outcomes
LO: Course Learning Outcomes

Prospective Student