It is aimed to learn how to apply Artificial Intelligence and Machine Learning techniques to solve engineering problems and design new products or systems. A research project demonstarting how computational learning algorithms can solve difficult problems in different fields is expected to be designed and implemented. At the end of this course, students will gain experience in how to apply various techniques wisely and how to evaluate performance. Students will also gain a deeper insight into why certain techniques may work or fail for certain types of problems.
Prerequisite(s)
IE3101 Introduction to Probability
Corequisite(s)
Course Code Course Name…
Special Requisite(s)
Phyton ya da Matlab knowledge
Instructor(s)
Professor Murat Ermiş
Course Assistant(s)
Schedule
The course is not offered this semester.
Office Hour(s)
The course is not offered this semester.
Teaching Methods and Techniques
Lecture, discussion, project
Principle Sources
E. Alpaydin (2004). Introduction to Machine Learning, MIT Press, 2004.
Other Sources
• T.M. Mitchell (1997). Machine Learning, McGraw-Hill.
• R.O. Duda, P.E. Hart, D.G, Stork (2001). Pattern Classification, Wiley-Interscience.
• K.P. Murphy (2012). Machine Learning: A probabilistic Perspective, MIT Press.
• D. Koller, and N. Friedman (2009). Probabilistic Graphical Models: Principles and Techniques, MIT Press.
• C.M. Bishop (2011). Pattern Recognition and Machine Learning, Springer.
Course Schedules
Week
Contents
Learning Methods
1. Week
Introduction to Machine Learning
Oral presentation
2. Week
Probability/Statistics Review and Estimation
Oral presentation
3. Week
Modeling Similarity
Oral presentation
4. Week
Fundamental Learning Models
Oral presentation
5. Week
Feature Extraction and Feature Selection, Examples from Machine Learning Research
Oral presentation, Laboratory
6. Week
Support Vector Machines
Oral presentation, Laboratory
7. Week
Artificial Neural Networks
Oral presentation, Laboratory
8. Week
Unsupervised Learning
Oral presentation, Laboratory
9. Week
Midterm Exam
Oral presentation, Laboratory
10. Week
Reinforcement and Ensemble Learning
Oral presentation, Laboratory
11. Week
Cost-sensitive Learning
Oral presentation, Laboratory
12. Week
Active Learning
Oral presentation, Laboratory
13. Week
Deep Learning
Oral presentation, Laboratory
14. Week
Project Presentations
Case study
15. Week
Final Exam
16. Week
Final Exam
17. Week
Final Exam
Assessments
Evaluation tools
Quantity
Weight(%)
Midterm(s)
1
20
Homework / Term Projects / Presentations
3
20
Project(s)
1
25
Attendance
14
5
Final Exam
1
30
Program Outcomes
PO-1
Ability to apply theoretical and practical knowledge gained by Mathematics, Science and their engineering fields and ability to use their knowledge in solving complex engineering problems.
PO-2
Ability of determining, defining, formulating and solving complex engineering problems; for that purpose develop the ability of selecting and implementing suitable models and methods of analysis.
PO-3
Ability of designing a complex system, process, device or product under real world constraints and conditions serving certain needs; for this purpose ability of applying modern design techniques
PO-4
Ability of selecting and using the modern techniques and devices which are necessary for analyzing and solving complex problems in engineering implementations; ability of efficient usage of information technologies.
PO-5
Ability of designing experiments, conducting tests, collecting data and analyzing and interpreting the solutions to investigate of complex engineering problems or discipline-specific research topics.
PO-6
Ability of working efficiently in intra-disciplinary and multi-disciplinary teams; individual working ability and habits.
PO-7
Ability of verbal and written communication skills; and at least one foreign language skills, ability to write effective reports and understand written reports, ability to prepare design and production reports, ability to make impressive presentation, ability to give and receive clear and understandable instructions
PO-8
Awareness of importance of lifelong learning; ability to access data, to follow up the recent innovation in science and technology for continuous self-improvement.
PO-9
Conformity to ethical principles; knowledge about occupational and ethical responsibility, and standards used in engineering applications.
PO-10
Knowledge about work life implementations such as project management, risk management and change management; awareness about entrepreneurship and innovativeness; knowledge about sustainable development.
PO-11
Knowledge about effects of engineering applications on health, environment and security in global and social dimensions, and on the problems of the modern age in engineering; awareness about legal outcomes of engineering solutions.
Learning Outcomes
LO-1
Recognize the characteristics of machine learning that make it useful to real-world problems.
LO-2
Characterize machine learning algorithms as supervised, and unsupervised.
LO-3
Effectively use machine learning toolboxes.
LO-4
Ability to use support vector machines.
LO-5
Understand the concept behind neural networks for learning non-linear functions.
LO-6
Understand reinforcement and ensemble learning algorithms.
LO-7
Be able to design and implement various machine learning algorithms in a range of real-world applications.