Computer Engineering
Course Details
KTO KARATAY UNIVERSITY
Mühendislik ve Doğa Bilimleri Fakültesi
Programme of Computer Engineering
Course Details
Mühendislik ve Doğa Bilimleri Fakültesi
Programme of Computer Engineering
Course Details
| Course Code | Course Name | Year | Period | Semester | T+A+L | Credit | ECTS |
|---|---|---|---|---|---|---|---|
| 05071390 | Introductıon to Deep Learnıng | 4 | Autumn | 7 | 3+0+0 | 3 | 5 |
| Course Type | Elective |
| Course Cycle | Bachelor's (First Cycle) (TQF-HE: Level 6 / QF-EHEA: Level 1 / EQF-LLL: Level 6) |
| Course Language | Turkish |
| Methods and Techniques | - |
| Mode of Delivery | Face to Face |
| Prerequisites | - |
| Coordinator | - |
| Instructor(s) | Asst. Prof. Ali Osman ÇIBIKDİKEN |
| Instructor Assistant(s) | - |
Course Instructor(s)
| Name and Surname | Room | E-Mail Address | Internal | Meeting Hours |
|---|---|---|---|---|
| Asst. Prof. Ali Osman ÇIBIKDİKEN | A-124 | [email protected] | 7585 | Monday 14.00-15.00 |
Course Content
Teaching students to; understand the concepts of TensorFlow, its main functions, operations and the execution pipeline, implement deep learning algorithms, understand neural networks and traverse the layers of data abstraction which will empower you to understand data like never before, build deep learning models in TensorFlow and interpret the results, understand the language and fundamental concepts of artificial neural networks
Objectives of the Course
Meeting with Deep Learning which is one of the most popular subjects in computer science. Learning TensorFlow that is the mostly choosen tool by professionals who work on Deep Learning.
Contribution of the Course to Field Teaching
| Basic Vocational Courses | |
| Specialization / Field Courses | |
| Support Courses | X |
| Transferable Skills Courses | |
| Humanities, Communication and Management Skills Courses |
Relationships between Course Learning Outcomes and Program Outcomes
| Relationship Levels | ||||
| Lowest | Low | Medium | High | Highest |
| 1 | 2 | 3 | 4 | 5 |
| # | Program Learning Outcomes | Level |
|---|---|---|
| P1 | Adequate knowledge in mathematics, science and related engineering discipline accumulation; theoretical and practical knowledge in these areas, complex engineering the ability to use in problems. | 5 |
| P3 | Ability to design a complex system, process, device or product to meet specific requirements under realistic constraints and conditions; ability to apply modern design methods for this purpose | 5 |
Course Learning Outcomes
| Upon the successful completion of this course, students will be able to: | |||
|---|---|---|---|
| No | Learning Outcomes | Outcome Relationship | Measurement Method ** |
| O1 | Basic concepts of Machine Learning and deep learning | P.1.17 | 1 |
| O2 | Having information about libraries where Deep Learning methods can be used | P.1.18 | 1 |
| O3 | To have knowledge about the use of Deep Learning methods in real application areas | P.3.25 | 1,7 |
| ** Written Exam: 1, Oral Exam: 2, Homework: 3, Lab./Exam: 4, Seminar/Presentation: 5, Term Paper: 6, Application: 7 | |||
Weekly Detailed Course Contents
| Week | Topics |
|---|---|
| 1 | Introduction to TensorFlow |
| 2 | Perceptrons |
| 3 | Activation Functions |
| 4 | Artificial Neural Networks |
| 5 | Optimization and Regularization - Overfitting and Capacity |
| 6 | Optimization and Regularization - Feature Selection |
| 7 | Optimization and Regularization - Regularization |
| 8 | Intro to Convolutional Neural Networks |
| 9 | Applications |
| 10 | Optimization Techniques for Training Deep Models |
| 11 | Backpropagation Algorithm |
| 12 | Graph Neural Networks and Generative Networks |
| 13 | Advanced Segmentation Techniques |
| 14 | Final |
Textbook or Material
| Resources | Simon J.D. Prince, "Understanding Deep Learning", MIT Press, https://udlbook.github.io/udlbook/, 2024. |
Evaluation Method and Passing Criteria
| In-Term Studies | Quantity | Percentage |
|---|---|---|
| Attendance | - | - |
| Laboratory | - | - |
| Practice | - | - |
| Course Specific Internship (If Any) | - | - |
| Homework | - | - |
| Presentation | - | - |
| Projects | - | - |
| Quiz | - | - |
| Midterms | 1 | 40 (%) |
| Final Exam | 1 | 60 (%) |
| Total | 100 (%) | |
ECTS / Working Load Table
| Quantity | Duration | Total Work Load | |
|---|---|---|---|
| Course Week Number and Time | 14 | 3 | 42 |
| Out-of-Class Study Time (Pre-study, Library, Reinforcement) | 14 | 2 | 28 |
| Midterms | 1 | 3 | 3 |
| Quiz | 0 | 0 | 0 |
| Homework | 0 | 0 | 0 |
| Practice | 0 | 0 | 0 |
| Laboratory | 0 | 0 | 0 |
| Project | 0 | 0 | 0 |
| Workshop | 0 | 0 | 0 |
| Presentation/Seminar Preparation | 0 | 0 | 0 |
| Fieldwork | 0 | 0 | 0 |
| Final Exam | 1 | 3 | 3 |
| Other | 0 | 0 | 0 |
| Total Work Load: | 76 | ||
| Total Work Load / 30 | 2,53 | ||
| Course ECTS Credits: | 3 | ||
Course - Learning Outcomes Matrix
| Relationship Levels | ||||
| Lowest | Low | Medium | High | Highest |
| 1 | 2 | 3 | 4 | 5 |
| # | Learning Outcomes | P1 | P3 |
|---|---|---|---|
| O1 | Basic concepts of Machine Learning and deep learning | 3 | - |
| O2 | Having information about libraries where Deep Learning methods can be used | - | 5 |
| O3 | To have knowledge about the use of Deep Learning methods in real application areas | 2 | - |