MACHINE LEARNING

Program Type:

Thesis

Course Code:

CSE585

Course Type:

Area Elective

P:

3

Lab:

0

Credits:

3

ECTS:

10

Course Language:

English

Course Objectives:

The aim of this course is to provide students the knowledege about the basic techniques and methodologies of machine learning and abilities to apply machine learning methods on practical problems.

Course Content:

Basic concepts and techniques of machine learning. Supervised learning tecniques. Concept and Decision Tree Learning. Bayesian approach in machine learning. Evolutionary approach and genetic programming. Neural Networks, Support Vector Machines and reinforcement learning. Unsupervised machine learning and clustering.

Teaching Methods:

Teaching Methods: 1: Lecture, 2: Discussion, 3: Seminar, 4: Research, 5: Simulation/Case Study/Role Playing, 6: Problem Session, 7: Invited Lecturer

Assessment Methods:

Assessment Methods: A: Exam, B: Assignment, C: Presentation, D: Research, E: Debate, F: Quiz, G: Participation

Vertical Tabs

Course Learning Outcomes

Course Learning Outcomes	Program Learning Outcomes	Teaching Methods	Assessment Methods
Knolwedege about the basic methodologies in machine learning.	3,4	1	A,C,D
Ability to use knowledge to formulate, and solve practical problems using machine learning techniques.	9,10	4	A,C,D

Course Flow

COURSE CONTENT
Week	Topics	Study Materials
1	Introduction	Textbook
2	Concept Learning	Textbook
3	Decision Tree Learning	Textbook
4	Genetic Algorithms and Programming	Textbook
5	Project Proposal Presentations	Textbook
6	Bayesian learning	Textbook
7	Bayesian Belief Networks	Textbook
8	Feed Forward Neural networks	Textbook
9	Recurrent Neural Networks	Textbook
10	Support Vector Machines	Textbook
11	Reinforcement Learning	Textbook
12	Unsupervised Learning	Textbook
13	Project Presentations	Textbook
14	Project Presentations	Textbook

Recommended Sources

RECOMMENDED SOURCES
Textbook	Machine Learning, McGraw-Hill, T. Mitchell (1997)
Additional Resources

Assessment

ASSESSMENT
IN-TERM STUDIES	NUMBER	PERCENTAGE
Assignment	1	20
Project	1	80
Total		100
CONTRIBUTION OF FINAL EXAMINATION TO OVERALL GRADE		35
CONTRIBUTION OF IN-TERM STUDIES TO OVERALL GRADE		65
Total		100

Course’s Contribution to Program

COURSE'S CONTRIBUTION TO PROGRAM
No		Program Learning Outcomes	Contribution
			1	2	3	4		5
1	Learning about empirical findings and theoretical perpectives in Cognitive Science.
2	Approaching findings, methods, opinions, and theories in Cognitive Science critically and multi-directionally.
3	Learning about research methods in Cognitive Science.						X
4	Searching the literature and reading, compehending, summarizing, and synthesizing contemporary articles in Cognitive Science.						X
5	Forming original research questions in Cognitive Science.
6	Relying on and converging findings from different disciplines in Cognitive Science in the process of forming a research question.
7	Conducting all steps of research in Cognitive Science.
8	Conducting research and applications ethically.
9	Using contemporary information technologies for following contemporary research and innovations.						X
10	Understanding that learning is necessary throughout the lifespan, and obtaining the skills to realize that.						X

ECTS

ECTS ALLOCATED BASED ON STUDENT WORKLOAD BY THE COURSE DESCRIPTION
Activities	Quantity	Duration (Hour)	Total Workload (Hour)
Course Duration	14	3	42
Hours for off-the-classroom study (Pre-study, practice)	14	5	70
Project	1	120	120
Assignment	1	15	15
Final examination	1	3	3
Total Work Load			250
Total Work Load / 25 (h)			10
ECTS Credit of the Course			10

Search form