Information Package / Course Catalogue
| Mechatronics and Robotics Engineering (English) (Thesis) | |||||
| Master | Length of the Programme: 2 | Number of Credits: 120 | TR-NQF-HE: Level 7 | QF-EHEA: Second Cycle | EQF: Level 7 |
Ders Genel Tanıtım Bilgileri
| School/Faculty/Institute | Graduate School | ||||
| Course Code | ITC 548 | ||||
| Course Title in English | Real World Applications of Machine Learning and Deep Learning | ||||
| Course Title in Turkish | Makine Öğrenimi ve Derin Öğrenmenin Gerçek Dünya Uygulamaları | ||||
| Language of Instruction | EN | ||||
| Type of Course | Flipped Classroom | ||||
| Level of Course | Intermediate | ||||
| Semester | Spring | ||||
| Contact Hours per Week |
|
||||
| Estimated Student Workload | 187 hours per semester | ||||
| Number of Credits | 7.5 ECTS | ||||
| Grading Mode | Standard Letter Grade | ||||
| Pre-requisites | None | ||||
| Expected Prior Knowledge | None | ||||
| Co-requisites | None | ||||
| Registration Restrictions | Only Graduate Students | ||||
| Overall Educational Objective | To develop technical skills and gain practical expertise necessary for designing machine and deep learning based intelligent systems that solve challenging engineering, science, health care and business problems. | ||||
| Course Description | This course covers the application of machine learning and deep learning approaches to real world problems. Topics include supervised learning, feed-forward neural networks, convolutional neural networks and recurrent neural networks, and their application to complex engineering problems in data-rich domains. | ||||
| Course Description in Turkish | Bu ders makine öğrenimi ve derin öğrenme yöntemlerinin gerçek dünya problemlerine uygulanmalarını içermektedir. Konular, gözetimli öğrenme, ileri-yönlü sinir ağları, evrişimsel sinir ağları ve yinelemeli sinir ağları ile bu yöntemlerin veri açısından zengin alanlarındaki karmaşık mühendislik problemlerine uygulanmasını içerir. |
Course Learning Outcomes and CompetencesUpon successful completion of the course, the learner is expected to be able to:1) Know basic principles of using machine learning and deep learning methods 2) Apply supervised learning methods and feed-forward neural networks to real world problems 3) Utilize convolutional neural networks in real world image processing/computer vision applications 4) Apply recurrent neural networks to natural language processing problems 5) Assess the performance of machine learning and deep learning methods in different domains |
| Program Learning Outcomes/Course Learning Outcomes | 1 | 2 | 3 | 4 | 5 |
|---|---|---|---|---|---|
| 1) An ability to develop and deepen one's knowledge in the field of mechatronics and robotics engineering at the level of expertise based on acquired undergraduate level qualifications. | |||||
| 2) An ability to acquire scientific and practical knowledge in mechatronics and robotics. | |||||
| 3) A comprehensive knowledge about analysis and modeling methods in mechatronics and their limitations. | |||||
| 4) An ability to design and apply analytical, modeling and experimental based research by analyzing and interpreting complex situations encountered in the design process. | |||||
| 5) An ability to transmit the process and results of the work of mechatronics and robotics systems systematically and clearly in written and oral form in national and international environments. | |||||
| 6) An ability to recognize social, scientific and ethical values in the stages of designing and realizing mechatronics and robotic systems and in all professional activities. | |||||
| 7) An ability to follow new and developing practices in the profession and to apply them in their work. | |||||
| 8) An ability to take leadership in multi-disciplinary teams, taking responsibility in the design and analysis of mechatronics and robotic systems in complex situations. | |||||
| 9) An ability to communicate verbally and in writing in English at least at the level of B2 of European Language Portfolio. | |||||
| 10) An understanding of the social and environmental aspects of mechatronics and robotics applications. |
Relation to Program Outcomes and Competences
| N None | S Supportive | H Highly Related |
| Program Outcomes and Competences | Level | Assessed by | |
| 1) | An ability to develop and deepen one's knowledge in the field of mechatronics and robotics engineering at the level of expertise based on acquired undergraduate level qualifications. | N | |
| 2) | An ability to acquire scientific and practical knowledge in mechatronics and robotics. | N | |
| 3) | A comprehensive knowledge about analysis and modeling methods in mechatronics and their limitations. | N | |
| 4) | An ability to design and apply analytical, modeling and experimental based research by analyzing and interpreting complex situations encountered in the design process. | N | |
| 5) | An ability to transmit the process and results of the work of mechatronics and robotics systems systematically and clearly in written and oral form in national and international environments. | N | |
| 6) | An ability to recognize social, scientific and ethical values in the stages of designing and realizing mechatronics and robotic systems and in all professional activities. | N | |
| 7) | An ability to follow new and developing practices in the profession and to apply them in their work. | N | |
| 8) | An ability to take leadership in multi-disciplinary teams, taking responsibility in the design and analysis of mechatronics and robotic systems in complex situations. | N | |
| 9) | An ability to communicate verbally and in writing in English at least at the level of B2 of European Language Portfolio. | N | |
| 10) | An understanding of the social and environmental aspects of mechatronics and robotics applications. | N |
| Prepared by and Date | , |
| Course Coordinator | TUNA ÇAKAR |
| Semester | Spring |
| Name of Instructor |
Course Contents
| Week | Subject |
| 1) | Introduction to Machine Learning and Deep Learning Concepts |
| 2) | Supervised Learning Applications |
| 3) | Feed-forward Neural Networks |
| 4) | Convolutional Neural Networks |
| 5) | Building Deep Learning Image Dataset |
| 6) | Performance Evaluation: Training, Testing and Validation |
| 7) | Real World Image Processing / Computer Vision Applications – Part 1 |
| 8) | Real World Image Processing / Computer Vision Applications – Part 2 |
| 9) | Real World Image Processing / Computer Vision Applications – Part 3 |
| 10) | Term Project Progress Presentations |
| 11) | Real World Natural Language Processing Applications – Part 1 |
| 12) | Real World Natural Language Processing Applications – Part 2 |
| 13) | Real World Natural Language Processing Applications – Part 3 |
| 14) | Term Project Presentations |
| 15) | Final Examination Period |
| 16) | Final Examination Period |
| Required/Recommended Readings | Introduction to Machine Learning, Ethem Alpaydın, MIT Press, 3rd Edition (2015) Deep Learning with Python, François Chollet, Manning, Second Edition (2021) | |||||||||||||||
| Teaching Methods | Flipped Classroom | |||||||||||||||
| Homework and Projects | Assignments, Term Project | |||||||||||||||
| Laboratory Work | None | |||||||||||||||
| Computer Use | Required | |||||||||||||||
| Other Activities | None | |||||||||||||||
| Assessment Methods |
|
|||||||||||||||
| Course Administration |
Academic dishonesty and plagiarism will be subject to Law on Higher Education Article 54. |
|||||||||||||||
ECTS Student Workload Estimation
| Activity | No/Weeks | Hours | Calculation | ||||
| No/Weeks per Semester | Preparing for the Activity | Spent in the Activity Itself | Completing the Activity Requirements | ||||
| Course Hours | 14 | 2 | 3 | 2 | 98 | ||
| Homework Assignments | 6 | 10 | 1 | 66 | |||
| Final Examination | 1 | 20 | 2 | 1 | 23 | ||
| Total Workload | 187 | ||||||
| Total Workload/25 | 7.5 | ||||||
| ECTS | 7.5 | ||||||