Applied Neural Computing (CMPE461) Course Detail

Course Name	Course Code	Season	Lecture Hours	Application Hours	Lab Hours	Credit	ECTS
Applied Neural Computing	CMPE461		2	2	0	3	5

Pre-requisite Course(s)
MATH275

Course Language	English
Course Type	N/A
Course Level	Natural & Applied Sciences Master's Degree
Mode of Delivery	Face To Face
Learning and Teaching Strategies	Lecture.
Course Coordinator
Course Lecturer(s)
Course Assistants
Course Objectives	This course has the objective to provide an introduction to neural network architectures, learning algorithms, and their applications.
Course Learning Outcomes	The students who succeeded in this course; Describe the concepts and techniques of neural networks Reason about the behavior of neural networks Evaluate which neural network model is appropriate to a particular application Evaluate pros and cons of neural network models Apply neural networks to particular applications Identify steps to take to improve performance of the algorithms
Course Content	Introduction to neural networks, perceptron learning rules, backpropagation algorithms, generalization and overtraining, adaptive linear filters, radial basis networks, self organizing networks, learning vector quantization, recurrent networks.

Weekly Subjects and Releated Preparation Studies

Week	Subjects	Preparation
1	Introduction to neural networks.	Chapter 1 (main text)
2	Perceptron learning rules	Chapter 5.1-5.3
3	Linear, nonlinear, and stochastic units in simple perceptrons and applications	Chapter 5.4-5.7
4	Backpropagation	Chapter 6.1
5	Variations on backpropagation and applications	Chapter 6.2, 6.3
6	Generalization and overtraining	Chapter 6.4-6.6
7	Recurrent networks	Chapter 7
8	Unsupervised learning	Chapter 8.1-8.3
9	Self organizing networks	Chapter 8.4
10	Adaptive linear filters	Chapter 9.1-9.4
11	Learning vector quantization	Chapter 6.3 (Other sources 2)
12	Radial basis networks	Chapter 5 (Other sources 1)
13	Applications of neural networks	Various sources
14	Applications of neural networks	Various sources

Sources

Course Book	1. Hertz, Krogh, & Palmer (1991) Introduction to the Theory of Neural Computation. Addison-Wesley.
Other Sources	2. 1. Bishop (2005). Neural Networks for Pattern Recognition. Oxford University Press.
	3. 2. Ripley, Ripley, & Hjort (1996). Pattern Recognition and Neural Networks. Cambridge University Press.
	4. 3. Haykin (1999). Neural Networks: A Comprehensive Foundation (2nd Edition) Macmillan.
	5. 4. Anderson, & Rosenfeld (1998) Neurocomputing: Foundations of Research, MIT Press, Cambridge.
	6. 5. Mitchell (1997). Machine Learning, McGraw Hill, New York.

Evaluation System

Requirements	Number	Percentage of Grade
Attendance/Participation	-	-
Laboratory	-	-
Application	-	-
Field Work	-	-
Special Course Internship	-	-
Quizzes/Studio Critics	-	-
Homework Assignments	2	10
Presentation	-	-
Project	2	40
Report	-	-
Seminar	-	-
Midterms Exams/Midterms Jury	1	20
Final Exam/Final Jury	1	30
Toplam	6	100

Percentage of Semester Work	70
Percentage of Final Work	30
Total	100

Course Category

Core Courses	X
Major Area Courses
Supportive Courses
Media and Managment Skills Courses
Transferable Skill Courses

The Relation Between Course Learning Competencies and Program Qualifications

#	Program Qualifications / Competencies	Level of Contribution
#	Program Qualifications / Competencies	1	2	3	4	5
1	An ability to apply knowledge of mathematics, science, and engineering.
2	An ability to design and conduct experiments, as well as to analyse and interpret data.
3	An ability to design a system, component, or process to meet desired needs.
4	An ability to function on multi-disciplinary domains.
5	An ability to identify, formulate, and solve engineering problems.
6	An understanding of professional and ethical responsibility.
7	An ability to communicate effectively.
8	Recognition of the need for, and an ability to engage in life-long learning.
9	A knowledge of contemporary issues.
10	An ability to use the techniques, skills, and modern engineering tools necessary for engineering practice.
11	Skills in project management and recognition of international standards and methodologies
12	An ability to produce engineering products or prototypes that solve real-life problems.
13	Skills that contribute to professional knowledge.
14	An ability to make methodological scientific research.
15	An ability to produce, report and present an original or known scientific body of knowledge.
16	An ability to defend an originally produced idea.

ECTS/Workload Table

Activities	Number	Duration (Hours)	Total Workload
Course Hours (Including Exam Week: 16 x Total Hours)	16	4	64
Laboratory
Application
Special Course Internship
Field Work
Study Hours Out of Class	16	1	16
Presentation/Seminar Prepration
Project	2	10	20
Report
Homework Assignments	2	4	8
Quizzes/Studio Critics
Prepration of Midterm Exams/Midterm Jury	1	7	7
Prepration of Final Exams/Final Jury	1	10	10
Total Workload			125