COURSE INTRODUCTION AND APPLICATION INFORMATION


Course Name
Machine Learning
Code
Semester
Theory
(hour/week)
Application/Lab
(hour/week)
Local Credits
ECTS
IES 511
Fall/Spring
3
0
3
7.5
Prerequisites
None
Course Language
English
Course Type
Elective
Course Level
Second Cycle
Mode of Delivery -
Teaching Methods and Techniques of the Course
Course Coordinator -
Course Lecturer(s) -
Assistant(s) -
Course Objectives The field of machine learning is concerned with the question of how to construct computer programs that improve automatically with experience. In recent years, many successful applications of machine learning have been developed, ranging from datamining programs that learn to detect fraudulent credit card transactions, to autonomous vehicles that learn to drive on public highways. At the same time, there have been important advances in the theory and algorithms that form the foundation of this field. The goal of this course is to provide an overview of the stateofart algorithms used in machine learning. Both the theoretical properties of these algorithms and their practical applications will be discussed.
Learning Outcomes The students who succeeded in this course;
  • Learn to use and discuss the basic techniques/algorithms of the field
  • Have knowledge of the advantages and limitations of different machine learning algorithms
  • Be able to evaluate potential applications of Machine Learning techniques
Course Description Supervised Learning: Decision trees, nearest neighbors, linear classifiers and kernels, neural networks, linear regression; learning theory. Unsupervised Learning: Clustering, graphical models, EM, PCA, factor analysis. Reinforcement Learning: Value iteration, policy iteration, TD learning, Q learning. Bayesian learning, online learning.
Related Sustainable Development Goals

 



Course Category

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

 

WEEKLY SUBJECTS AND RELATED PREPARATION STUDIES

Week Subjects Required Materials
1 Introduction, Machine Learning examples T. Mitchell, Machine Learning;, McGrawHill, 1997, hardcover ISBN 0070428077 (Ch. 1)
2 Concept Learning, Inductive Bias T. Mitchell, Machine Learning;, McGrawHill, 1997, hardcover ISBN 0070428077 (Ch. 2)
3 Decision Trees T. Mitchell, Machine Learning;, McGrawHill, 1997, hardcover ISBN 0070428077 (Ch. 3)
4 Artificial Neural Networks T. Mitchell, Machine Learning;, McGrawHill, 1997, hardcover ISBN 0070428077 (Ch. 4)
5 Bayesian Learning T. Mitchell, Machine Learning;, McGrawHill, 1997, hardcover ISBN 0070428077 (Ch. 6)
6 Instance Based Learning T. Mitchell, Machine Learning;, McGrawHill, 1997, hardcover ISBN 0070428077 (Ch. 8)
7 Ara sınav / Midterm
8 Reinforcement Learning T. Mitchell, Machine Learning;, McGrawHill, 1997, hardcover ISBN 0070428077 (Ch. 13)
9 Evolutionary Algorithms T. Mitchell, Machine Learning;, McGrawHill, 1997, hardcover ISBN 0070428077 (Ch. 9)
10 Learning Theory T. Mitchell, Machine Learning;, McGrawHill, 1997, hardcover ISBN 0070428077 (Ch. 7)
11 Discussions, Research and Presentations
12 Discussions, Research and Presentations
13 Discussions, Research and Presentations
14 Discussions, Research and Presentations
15 Review for Final Exam
16 Review of the Semester  
Course Notes/Textbooks The textbook referenced above and course slides
Suggested Readings/Materials 1) Introduction to Machine Learning, Ethem Alpaydın, The MIT Press, October 2004, ISBN 0262012111. 2) Related Research Papers

 

EVALUATION SYSTEM

Semester Activities Number Weigthing
Participation
Laboratory / Application
Field Work
Quizzes / Studio Critiques
Portfolio
Homework / Assignments
Presentation / Jury
1
20
Project
1
25
Seminar / Workshop
Oral Exam
Midterm
1
30
Final Exam
Total

Weighting of Semester Activities on the Final Grade
75
Weighting of End-of-Semester Activities on the Final Grade
25
Total

ECTS / WORKLOAD TABLE

Semester Activities Number Duration (Hours) Workload
Course Hours
(Including exam week: 16 x total hours)
16
3
48
Laboratory / Application Hours
(Including exam week: 16 x total hours)
16
Study Hours Out of Class
15
6
90
Field Work
Quizzes / Studio Critiques
Portfolio
Homework / Assignments
Presentation / Jury
1
20
Project
1
25
Seminar / Workshop
Oral Exam
Midterms
1
15
Final Exams
    Total
198

 

COURSE LEARNING OUTCOMES AND PROGRAM QUALIFICATIONS RELATIONSHIP

#
Program Competencies/Outcomes
* Contribution Level
1
2
3
4
5
1

To develop and deepen his/her knowledge on theories of mathematics and statistics and their applications in level of expertise, and to obtain unique definitions which bring innovations to the area, based on master level competencies,

2

To have the ability of original, independent and critical thinking in Mathematics and Statistics and to be able to develop theoretical concepts,

3

To have the ability of defining and verifying problems in Mathematics and Statistics,

4

With an interdisciplinary approach, to be able to apply theoretical and applied methods of mathematics and statistics in analyzing and solving new problems and to be able to discover his/her own potentials with respect to the application,

5

In nearly every fields that mathematics and statistics are used, to be able to execute, conclude and report a research, which requires expertise, independently,

6

To be able to evaluate and renew his/her abilities and knowledge acquired in the field of Applied Mathematics and Statistics with critical approach, and to be able to analyze, synthesize and evaluate complex thoughts in a critical way,

7

To be able to convey his/her analyses and methods in the field of Applied Mathematics and Statistics to the experts in a scientific way,

8

To be able to use national and international academic resources (English) efficiently, to update his/her knowledge, to communicate with his/her native and foreign colleagues easily, to follow the literature periodically, to contribute scientific meetings held in his/her own field and other fields systematically as written, oral and visual.

9

To be familiar with computer software commonly used in the fields of Applied Mathematics and Statistics and to be able to use at least two of them efficiently,

10

To contribute the transformation process of his/her own society into an information society and the sustainability of this process by introducing scientific, technological, social and cultural advances in the fields of Applied Mathematics and Statistics,

11

As having rich cultural background and social sensitivity with a global perspective, to be able to evaluate all processes efficiently, to be able to contribute the solutions of social, scientific, cultural and ethical problems and to support the development of these values,

12

As being competent in abstract thinking, to be able to connect abstract events to concrete events and to transfer solutions, to analyze results with scientific methods by designing experiment and collecting data and to interpret them,

13

To be able to produce strategies, policies and plans about systems and topics in which mathematics and statistics are used and to be able to interpret and develop results,

14

To be able to evaluate, argue and analyze prominent persons, events and phenomena, which play an important role in the development and combination of the fields of Mathematics and Statistics, within the perspective of the development of other fields of science,

15

In Applied Mathematics and Statistics, to be able to sustain scientific work as an individual or a group, to be effective in all phases of an independent work, to participate decision-making process and to make and execute necessary planning within an effective time schedule.

*1 Lowest, 2 Low, 3 Average, 4 High, 5 Highest