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
Fall/Spring
3
0
3
5

Prerequisites
None
Course Language
English
Course Type
Elective
Course Level
First Cycle
Course Coordinator
Course Lecturer(s)
Assistant(s) -
Course Objectives The course covers key background topics from advanced machine learning including sampling and information theory, digital filtering and discrete Fourier transform, basics of vector and matrix manipulations, numerical optimization, and the fundamentals of the theory of statistical learning.
Course Description The students who succeeded in this course;
  • will be able to apply principles of signal sampling and filtering in data processing algorithms,
  • will be able to use vector and matrix quantities in data processing algorithms,
  • will be able to use numerical optimization methods in machine learning algorithms,
  • will be able to describe the main principles of the theory of statistical learning,
  • will be able to contrast machine learning algorithms wıth respect to bias-variance trade-off, model complexity, and cross-validation error.
Course Content The following topics will be included: sampling and information theory, digital filters and discrete Fourier transform, basics of vector and matrix manipulations, basics of numerical optimization, principles of statistical learning theory.

 



Course Category

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

 

WEEKLY SUBJECTS AND RELATED PREPARATION STUDIES

Week Subjects Related Preparation
1 Introduction: What is Machine Learning?
2 Basics of signal sampling - sampling rate, Nyquist frequency, resolution of signals and images, Shannon information, efficient codes, data compression Chapter 1. Signals & Systems. Oppenheim & Willsky. ISBN 0136511759.
3 Introduction to digital filters, convolution, LTI theory, 1D and 2D filters, linear and nonlinear filters Chapter 2. Signals & Systems. Oppenheim & Willsky. ISBN 0136511759.
4 Fourier transform, discrete Fourier transform, spectrum of signals, spectrum of images, complex numbers Chapter 3. Signals & Systems. Oppenheim & Willsky. ISBN 0136511759.
5 Basics of linear algebra, row and column vectors, matrices, matrix multiplication, outer multiplication, norm Linear Algebra and Its Applications, David C. Lay, Steven R. Lay, Judi J. McDonald, Pearson, 5th Edition
6 Basics of numerical optimization, optimality conditions, KKT conditions, gradient descent, convex optimization programs Chapter 1. Sections 1.1-1.4, Chapter 4. Sections 4.3, 4.4. Nonlinear Programming, D. Bertsekas, Athena Scientific, 3rd Edition
7 Midterm exam
8 Primal-dual theory, large scale optimization, stochastic gradient descent Chapter 2. Chapter 6. Sections 6.1-6.4. Nonlinear Programming, D. Bertsekas, Athena Scientific, 3rd Edition
9 Review of probability, random variables, probability distributions, Bayes theorem, expectation values, LLN, CLT, Markov, Jensen, Chernoff and Hoeffding inequalities Statistics for Engineers and Scientists, William Navidi, 4th Ed., Mc-Graw Hill.
10 Introduction to statistical learning theory - learning as statistical activity, supervised and unsupervised learning, regression and classification Chapter 2. Sections 2.1-2.3. The Elements of Statistical Learning, T. Hastie, R. Tibshirani, J. Friedman, ISBN 9780387216065
11 Statistical decision theory, function estimation, statistical models, restricted estimators, dimensionality curse, bias-variance trade-off Chapter 2. Sections 2.4-2.6, 2.8, Chapter 7. Section 7.2. The Elements of Statistical Learning, T. Hastie, R. Tibshirani, J. Friedman, ISBN 9780387216065
12 Model assessment and selection, effective model dimension, AIC, BIC, Vapnik-Chervonenkis dimensions Chapter 7. Sections 7.2-7.7. The Elements of Statistical Learning, T. Hastie, R. Tibshirani, J. Friedman, ISBN 9780387216065
13 Vapnik-Chervonenkis dimensions, cross-validation and why it works, bootstrap methods Chapter 7. Sections 7.9-7.11. The Elements of Statistical Learning, T. Hastie, R. Tibshirani, J. Friedman, ISBN 9780387216065
14 General semester review
15 General semester review
16 General semester review

 

Course Notes/Textbooks

Lecture notes

Suggested Readings/Materials

A. Oppenheim, A. Willsky, Signals & Systems, Pearson, 1996, ISBN 0136511759; 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 Weigthing
Participation
Laboratory / Application
Field Work
Quizzes / Studio Critiques
Homework / Assignments
5
20
Presentation / Jury
Project
Seminar / Workshop
Portfolios
Midterms / Oral Exams
1
30
Final / Oral Exam
1
50
Total

Weighting of Semester Activities on the Final Grade
6
50
Weighting of End-of-Semester Activities on the Final Grade
1
50
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
14
2
Field Work
Quizzes / Studio Critiques
Homework / Assignments
5
6
Presentation / Jury
Project
Seminar / Workshop
Portfolios
Midterms / Oral Exams
1
20
Final / Oral Exam
1
24
    Total
150

 

COURSE LEARNING OUTCOMES AND PROGRAM QUALIFICATIONS RELATIONSHIP

#
Program Competencies/Outcomes
* Contribution Level
1
2
3
4
5
1 Adequate knowledge in Mathematics, Science and Software Engineering; ability to use theoretical and applied information in these areas to model and solve Software Engineering problems
2 Ability to identify, define, formulate, and solve complex Software Engineering problems; ability to select and apply proper analysis and modeling methods for this purpose
3 Ability to design, implement, verify, validate, measure and maintain a complex software system, process or product under realistic constraints and conditions, in such a way as to meet the desired result; ability to apply modern methods for this purpose
4 Ability to devise, select, and use modern techniques and tools needed for Software Engineering practice
5 Ability to design and conduct experiments, gather data, analyze and interpret results for investigating Software Engineering problems
6 Ability to work efficiently in Software Engineering disciplinary and multi-disciplinary teams; ability to work individually
7 Ability to communicate effectively in Turkish, both orally and in writing; knowledge of a minimum of two foreign languages
8 Recognition of the need for lifelong learning; ability to access information, to follow developments in science and technology, and to continue to educate him/herself
9 Awareness of professional and ethical responsibility
10 Information about business life practices such as project management, risk management, and change management; awareness of entrepreneurship, innovation, and sustainable development
11 Knowledge about contemporary issues and the global and societal effects of engineering practices on health, environment, and safety; awareness of the legal consequences of Software Engineering solutions

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