Department of Computer Engineering

CE 395 | Course Introduction and Application Information

Course Name

Special Topics in Machine Learning

Code	Semester	Theory (hour/week)	Application/Lab (hour/week)	Local Credits	ECTS
CE 395	SPRING	3	0	3	5

Prerequisites	None
Course Language	English
Course Type	ELECTIVE_COURSE
Course Level	First Cycle
Mode of Delivery
Teaching Methods and Techniques of the Course	Problem solving Lecture / Presentation
National Occupational Classification Code	-
Course Coordinator	Dr. Öğr. Üyesi Kaya Oğuz
Course Lecturer(s)	-
Assistant(s)	-

Course Objectives

This course provides the mathematical and conceptual foundations for advanced machine learning methods. It covers sampling and information theory, digital filtering and the discrete Fourier transform, vector and matrix manipulations, numerical optimization, and the foundations of statistical learning theory.

Learning Outcomes

The students who succeeded in this course;

Name	Description	PC Sub	* Contribution Level
Name	Description	PC Sub	1	2	3	4	5
LO1	Be able to apply signal sampling and filtering principles by being involved in data processing algorithms.			X
LO2	Be able to use vectors and matrices in data processing algorithms.				X
LO3	Be able to use numerical optimization methods for machine learning algorithms.				X
LO4	Describe the principles of statistical learning theory.			X
LO5	Compare machine learning algorithms in terms of bias-variance trade-off, model complexity, and cross-validation.					X

Course Description

The following topics will be included in the syllabus: sampling and information theory, digital filtering and the discrete Fourier transform, basic vector and matrix operations, fundamentals of numerical optimization, fundamentals of statistical learning theory.

Related Sustainable Development Goals

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

WEEKLY SUBJECTS AND RELATED PREPARATION STUDIES

Week	Subjects	Required Materials	Learning Outcome
1	Introduction: What is machine learning?	Chapter 1. T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning. ISBN 9780387216065	45fdb90f
2	Signal sampling fundamentals - sampling frequency, Nyquist frequency, signal and image resolution, Shannon information theory, efficient codes, data compression	Chapter 1. Signals & Systems. Oppenheim & Willsky. ISBN 0136511759.	2da6abf8
3	Introduction to digital filtering, convolution, linear and time invariant system theory, 1D and 2D filters, linear and nonlinear filters	Chapter 2. Signals & Systems. Oppenheim & Willsky. ISBN 0136511759.	2da6abf8
4	Fourier transform, discrete Fourier transform, spectrum of signal and image, complex numbers	Chapter 3. Signals & Systems. Oppenheim & Willsky. ISBN 0136511759.	2da6abf8
5	Summary of linear algebra - row and column vectors, matrices, matrix multiplication, the exclusion product, norm	Linear Algebra and Its Applications, David C. Lay, Steven R. Lay, Judi J. McDonald, Pearson, 5th Edition	6ee14736
6	Fundamentals of numerical optimization – optimality conditions, KKT conditions, slope descent optimization, convex optimization programs	Chapter 1. Part 1.1-1.4. Chapter 4. Part 4.3, 4.4. Nonlinear Programming, D. Bertsekas, Athena Scientific, 3rd Edition	fc82ce4f
7	Midterm exam		6ee14736
8	Primal-dual theory, large-scale optimization, stochastic gradient descent method	Chapter 2. Chapter 6. Part 6.1-6.4. Nonlinear Programming, D. Bertsekas, Athena Scientific, 3rd Edition	fc82ce4f
9	Summary of probability, random variables and probability distributions, Bayes' theorem, expected values, Law of Large Numbers, Central Limit Theorem, Markov, Jensen, Chernoff and Hoeffding inequalities	Statistics for Engineers and Scientists, William Navidi, 4th Ed., Mc-Graw Hill.	45fdb90f
10	Introduction to statistical learning theory - learning as a statistical activity, supervised and unsupervised learning, regression and classification	Chapter 2. Part 2.1-2.3. The Elements of Statistical Learning, T. Hastie, R. Tibshirani, J. Friedman, ISBN 9780387216065	45fdb90f
11	Statistical decision theory, function estimation, statistical models, restricted estimators, curse of dimensionality, bias-variance trade-off	Chapter 2. Part 2.4-2.6, 2.8. Chapter 7. Part 7.2. The Elements of Statistical Learning, T. Hastie, R. Tibshirani, J. Friedman, ISBN 9780387216065	9a3a15f2
12	Model evaluation and selection, effective model sizes, AIC, BIC, Vapnik-Chervonenkis size	Chapter 7. Part 7.2-7.7. The Elements of Statistical Learning, T. Hastie, R. Tibshirani, J. Friedman, ISBN 9780387216065	9a3a15f2
13	Vapnik-Chervonenkis dimension, cross-validation and its properties, bootstrap methods	Chapter 7. Part 7.9-7.11. The Elements of Statistical Learning, T. Hastie, R. Tibshirani, J. Friedman, ISBN 9780387216065	9a3a15f2
14	Review of the semester		2da6abf8
15	Review of the semester		fc82ce4f
16	Final exam		9a3a15f2

Course Notes/Textbooks

A. Oppenheim; A. Willsky; Signals & Systems; Pearson; 1996; ISBN 0136511759

Suggested Readings/Materials

D. Lay; S. Lay; J. McDonald; Linear Algebra and Its Applications; Pearson; 5th Edition; 2015; ISBN 9780321982384
D. Bertsekas; Nonlinear Programming; Athena Scientific; 3rd Edition; 2016; ISBN 9781886529052
W. Navidi; Statistics for Engineers and Scientists; Mc-Graw Hill; 3rd Edition; 2010; ISBN 9780073376332
T. Hastie; R. Tibshirani; J. Friedman; The Elements of Statistical Learning; Springer; 2013; ISBN 9780387216065.

EVALUATION SYSTEM

Semester Activities	Number	Weighting	LO1	LO2	LO3	LO4	LO5
Homework / Assignments	5	30	X	X	X	X	X
Midterm	1	30	X	X	X
Final Exam	1	40			X	X	X
Total	7	100

ECTS / WORKLOAD TABLE

Semester Activities	Number	Duration (Hours)	Workload
Participation	-	-	-
Theoretical Course Hours	16	3	48
Laboratory / Application Hours	-	-	-
Study Hours Out of Class	14	2	28
Field Work	-	-	-
Quizzes / Studio Critiques	-	-	-
Portfolio	-	-	-
Homework / Assignments	5	6	30
Presentation / Jury	-	-	-
Project	-	-	-
Seminar / Workshop	-	-	-
Oral Exams	-	-	-
Midterms	1	20	20
Final Exam	1	24	24
		Total	150

COURSE LEARNING OUTCOMES AND PROGRAM QUALIFICATIONS RELATIONSHIP

#	PC Sub	Program Competencies/Outcomes	* Contribution Level
			1	2	3	4	5
No program competency data found.

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

NEWSALL NEWS

Home kitchens will be like ‘restaurant kitchens’

Esra-Melis Sarıhan sisters, graduates of Izmir University of Economics (IUE), developed an application called ‘Yedir’ that will bring home cooks ...

Detail

Watch out for pandemic scams

Fake job postings that promise people to work from home have been the latest tactic of scammers, who are looking ...

Detail

IZMIR UNIVERSITY OF ECONOMICS GÜZELBAHÇE CAMPUS

Details

GLOBAL CAREER

As Izmir University of Economics transforms into a world-class university, it also raises successful young people with global competence.

More..

CONTRIBUTION TO SCIENCE

Izmir University of Economics produces qualified knowledge and competent technologies.

More..

VALUING PEOPLE

Izmir University of Economics sees producing social benefit as its reason for existence.

More..

BENEFIT TO SOCIETY

Transferring 22 years of power and experience to social work…

More..

You are one step ahead with your graduate education at Izmir University of Economics.

Master Programs Doctorate Programs