The aim of this graduate course is to teach various techniques for learning from data by using basic and advanced concepts in machine learning. The module in which different techniques and algortihms are compared and applications are considered basicly addresses the question how to enable computers to learn from past experience.
Prerequisite(s)
Corequisite(s)
Special Requisite(s)
Instructor(s)
Dr.Ögr.Üyesi İsmail KOÇ
Course Assistant(s)
Schedule
Office Hour(s)
Teaching Methods and Techniques
Lectures, projects, readings (journal and conference papers) and discussions
Principle Sources
Ethem Alpaydın, Introduction to Machine Learning, MIT Press
Other Sources
R. O. Duda, P. E. Hart, D. G. Stork, Pattern Classification, 2nd Edition, Wiley Interscience, 2001
Tom Mitchell. Machine Learning. McGraw Hill, 1997, 0070428077
Course Schedules
Week
Contents
Learning Methods
1. Week
Introduction to Machine Learning, general approach and motivation
Oral Presentation, Handout (syllabus)
2. Week
Supervised Learning I, Linear Regression, Least Mean Square Algorithm
Oral Presentation, Handout (related paper(s))
3. Week
Supervised Learning II, Classification and Logistic Regression
Oral Presentation, Handout (related paper(s)), discussion, Final Project Proposal
an ability to apply knowledge from undergraduate and graduate engineering and other disciplines to identify, formulate, and solve novel and complex electrical/computer engineering problems that require advanced knowledge within the field
PO-2
knowledge of advanced topics within at least two subdisciplines of computer engineering
PO-3
the ability to understand and integrate new knowledge within the field;
PO-4
the ability to apply advanced technical knowledge in multiple contexts
PO-5
a recognition of the need for, and an ability to engage in, life-long learning
PO-6
the ability to plan and conduct an organized and systematic study on a significant topic within the field
PO-7
an ability to convey technical material through formal written reports which satisfy accepted standards for writing style
PO-8
the ability to analyze and use existing literature
PO-9
the ability to demonstrate effective oral communication skills
PO-10
the ability to stay abreast of advancements in the area of computer engineering
Learning Outcomes
LO-1
to apply knowledge of mathematics and computing to design and analysis of machine learning methods
LO-2
to analyze a problem and identify the computing requirements appropriate for its solution
LO-3
to demonstrate a high standard of professional and research ethics
LO-4
to design and conduct experiments and numerical tests of machine learning methods, and to analyze and interpret their results
