Deep Learning and Its Applications
Computer Engineering (Ph.D.)
Institute of Natural and Applied Sciences
Third Cycle (Doctorate Degree)
| Course Unit Title | Course Unit Code | Type of Course Unit | Level of Course Unit | Year of Study | Semester | ECTS Credits |
|---|---|---|---|---|---|---|
| Deep Learning and Its Applications | BLM606 | Elective | Doctorate degree | 1 | Spring | 8 |
Name of Lecturer(s)
Prof. Dr. Yaşar BECERİKLİ
Learning Outcomes of the Course Unit
1) Proposes learning methods for problem solving
2) Analyzes performance of different leaning methods
3) learns deep learning princples
4) learns computer vision topic
5) Literature information about Deep learning
Program Competencies-Learning Outcomes Relation
| Program Competencies | |||||||||||||
| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | ||
| Learning Outcomes | |||||||||||||
| 1 | High | Middle | Middle | Middle | Middle | Middle | Middle | No relation | No relation | High | No relation | Low | |
| 2 | High | Middle | Middle | Middle | Middle | Middle | Middle | No relation | No relation | High | No relation | Low | |
| 3 | High | Middle | Middle | Middle | Middle | Middle | Middle | No relation | No relation | High | No relation | Low | |
| 4 | High | Middle | Middle | No relation | Middle | Middle | Middle | No relation | No relation | High | No relation | Low | |
| 5 | High | Middle | Middle | Low | Middle | Middle | Middle | No relation | No relation | High | No relation | Low | |
Mode of Delivery
Face to Face
Prerequisites and Co-Requisites
None
Recommended Optional Programme Components
Machine Learning
Course Contents
General Information, Introduction to Pattern Recognition, machine learning, and Optimization. Basics of learning and deep learning. Classification, Linear classification, loss function. Multilayer Neural Networks (MLPs), Recurrent Neural Networks (MLP). Deep Neural Networks (DeNNs), Convulational Neural Networks (CoNNs). Learning Algortihms in Recurrent Neural Networks (MLP). Object detection and recognition. Deep Face Recognition. 3D Convulational Neural Networks. Applications.
Weekly Schedule
1) General Information, Introduction to Pattern Recognition, machine learning, and Optimization2) BAsics of learning and deep learning
3) Classification, Linear classification, loss function
4) Perceptron Networks, perceptron learning, multilayer perceptron
5) Gradient Descent Algorithms and optimization
6) Multilayer Neural Networks (MLPs), Recurrent Neural Networks (MLP),
7) Deep Neural Networks (DeNNs), Convulational Neural Networks (ConNNs)
8) Learning Algortihms in Recurrent Neural Networks (RNN)
9) Midterm
10) Deep Learning Applications and Libraries (Keras, TensorFlow, CAffe, Theano vb),, Object Detection and YOLO algoritms
11) Object Recognition and Deep Learning
12) Bioinformatics and deep learning
13) Deep Face Recognition
14) 3D Convulational Neural Networks
15) Other Applications
16) Review of the course
Recommended or Required Reading
Planned Learning Activities and Teaching Methods
1) Lecture
2) Question-Answer
3) Discussion
4) Demonstration
5) Group Study
6) Simulation
7) Self Study
8) Problem Solving
Assessment Methods and Criteria
Contribution of Semester Studies to Course Grade |
50% |
|||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
||||||||||||
Contribution of Final Examination to Course Grade |
50% |
|||||||||||
Total | 100% | |||||||||||
Language of Instruction
Turkish
Work Placement(s)
Not Required