Department of Biomedical Engineering

CE 344 | Course Introduction and Application Information

Course Name

Advanced Automatic Learning

Code	Semester	Theory (hour/week)	Application/Lab (hour/week)	Local Credits	ECTS
CE 344	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	Discussion Problem solving Question & Answer Criticism Lecture/Presentation
National Occupational Classification Code	-
Course Coordinator	Dr. Öğr. Üyesi Kutluhan Erol
Course Lecturer(s)	Dr. Öğr. Üyesi Kutluhan Erol
Assistant(s)	-

Course Objectives

The aim of this course is to provide an advanced knowledge of algorithms and techniques in the field of modern machine learning. Both the basic and advanced theoretical aspects of these algorithms and techniques, as well as the practical applications resulting from this theory will be discussed.

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	Describe a wide range of advanced machine learning algorithms and techniques,	1.5		X
LO2	Be able to apply algorithms and techniques in the field of advanced machine learning,	4					X
LO3	Compare different algorithms and techniques in the field of advanced machine learning,	2		X
LO4	Design various advanced machine learning algorithms for specific problems,	3.1	X
LO5	Evaluate practical applications of advanced machine learning techniques.	5.2			X

Course Description

This course covers advanced machine learning topics, including collecting training data, learning to infer statistical structure from data, overfitting, parametric models and parameter selection, validation, regression, classification, nonparametric models, and clustering.

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 to machine learning. Probability repetition	Part 1-2. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	e219e649
2	Generative models for discrete data. Gaussian models	Part 3-4. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	e219e649
3	Bayesian and frequentist statistics	Part 5-6. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	e219e649
4	Linear and logistic regression	Part 7-8. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	896e6dff
5	Generalized linear models and exponential families	Part 9. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	896e6dff
6	Graphical models: Markov random field and Bayesian networks	Part 10-19. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	14601732
7	Mixture models and EM algorithm	Part 11. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	14601732
8	Hidden linear and sparse linear models	Part 12-13. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	14601732
9	Markov and hidden Markov models	Part 17. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	1b81476f
10	Exact inference for graphical models. Variational inference	Part 20-21-22. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	c282d781
11	Exact inference for graphical models. Variational inference	Part 20-21-22. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	c282d781
12	Monte Carlo and Markov chain Monte Carlo inference	Part 23-24. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	1b81476f
13	Core models	Part 14. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	e219e649
14	Grouping	Part 25. Machine Learning: A Probabilistic Perspective. K. Murphy. ISBN: 9780262018029	c282d781
15	Review of the period		1b81476f
16	Final Exam		1b81476f

Course Notes/Textbooks	Kevin Murphy; Machine Learning: A Probabilistic Perspective; MIT Press; 2012; ISBN: 9780262018029
Suggested Readings/Materials	Christopher M. Bishop; Pattern Recognition and Machine Learning; Springer; 2006; ISBN: 9780387310732

EVALUATION SYSTEM

Semester Activities	Number	Weighting	LO1	LO2	LO3	LO4	LO5
Quizzes / Studio Critiques	4	12	X				X
Homework / Assignments	2	10		X		X
Project	1	40		X	X	X	X
Final Exam	1	38	X		X
Total	8	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	4	2	8
Portfolio	-	-	-
Homework / Assignments	2	5	10
Presentation / Jury	-	-	-
Project	1	30	30
Seminar / Workshop	-	-	-
Oral Exams	-	-	-
Midterms	-	-	-
Final Exam	1	26	26
		Total	150

COURSE LEARNING OUTCOMES AND PROGRAM QUALIFICATIONS RELATIONSHIP

#	PC Sub	Program Competencies/Outcomes	* Contribution Level
#	PC Sub	Program Competencies/Outcomes	1	2	3	4	5
1	Engineering Knowledge: Knowledge of mathematics, science, basic engineering, computation, and related engineering discipline-specific topics; the ability to apply this knowledge to solve complex engineering problems.
	1	Mathematics
	2	Science
	3	Basic Engineering
	4	Computation
	5	Related engineering discipline-specific topics		LO1
	6	The ability to apply this knowledge to solve complex engineering problems
2	Problem Analysis: Ability to identify, formulate and analyze complex engineering problems using basic knowledge of science, mathematics and engineering, and considering the UN Sustainable Development Goals relevant to the problem being addressed.			LO3
3	Engineering Design: The ability to devise creative solutions to complex engineering problems; the ability to design complex systems, processes, devices or products to meet current and future needs, considering realistic constraints and conditions.
	1	Ability to design creative solutions to complex engineering problems	LO4
	2	Ability to design complex systems, processes, devices or products to meet current and future needs, considering realistic constraints and conditions
4	Use of Techniques and Tools: Ability to select and use appropriate techniques, resources, and modern engineering and computing tools, including estimation and modeling, for the analysis and solution of complex engineering problems, while recognizing their limitations.						LO2
5	Research and Investigation: Ability to use research methods to investigate complex engineering problems, including literature research, designing and conducting experiments, collecting data, and analyzing and interpreting results.
	1	Literature research for the study of complex engineering problems
	2	Designing experiments			LO5
	3	Ability to use research methods, including conducting experiments, collecting data. analyzing and interpreting results
6	Global Impact of Engineering Practices: Knowledge of the impacts of engineering practices on society, health and safety, economy, sustainability, and the environment, within the context of the UN Sustainable Development Goals; awareness of the legal implications of engineering solutions.
	1	Knowledge of the impacts of engineering practices on society, health and safety, economy, sustainability, and the environment, within the context of the UN Sustainable Development Goals
	2	Awareness of the legal implications of engineering solutions
7	Ethical Behavior: Acting in accordance with the principles of the engineering profession, knowledge about ethical responsibility; awareness of being impartial, without discrimination, and being inclusive of diversity.
	1	Acting in accordance with the principles of the engineering profession, knowledge about ethical responsibility ethical responsibility
	2	Awareness of being impartial and inclusive of diversity, without discriminating on any subject
8	Individual and Teamwork: Ability to work effectively, individually and as a team member or leader on interdisciplinary and multidisciplinary teams (face-to-face, remote or hybrid).
	1	Ability to work individually and within the discipline
	2	Ability to work effectively as a team member or leader in multidisciplinary teams (face-to-face, remote or hybrid)
9	Verbal and Written Communication: Taking into account the various differences of the target audience (such as education, language, profession) on technical issues.
	1	Ability to communicate verbally
	2	Ability to communicate effectively in writing
10	Project Management: Knowledge of business practices such as project management and economic feasibility analysis; awareness of entrepreneurship and innovation.
	1	Knowledge of business practices such as project management and economic feasibility analysis
	2	Awareness of entrepreneurship and innovation
11	Lifelong Learning: Lifelong learning skills that include being able to learn independently and continuously, adapting to new and developing technologies, and thinking questioningly about technological changes.