Faculty of Engineering and Natural Sciences · Computer Engineering · Undergraduate
ECTS: 5 T+P+L: 2+0+1 Departmental Elective
Coordinator: Dr. Öğr. Üyesi Sahra TİLKİ
Teaching Methods
ExpressionExercise and PracticePresentationCase StudySelf studyProblem Solving
Assessment & Evaluation
Project / DesignTesting (Essay / Tests: True-Falls, multiple-choice, short answer, matching)
ECTS / Workload
| Activity | Quantity | Duration (h) | Total Workload |
|---|---|---|---|
| Course Duration (Including Exam Week) | 16 | 3 | 48 |
| Out of Class Study Period | 16 | 2 | 32 |
| Midterm | 1 | 2 | 2 |
| Quiz | 0 | 0 | 0 |
| Assignment | 1 | 10 | 10 |
| Practice | 0 | 0 | 0 |
| Final | 1 | 2 | 2 |
Course Schedule
| Week | Subject | Preparation |
|---|---|---|
| 1 | Introduction to Neural Networks and Deep Learning and Basic Concepts | Introduction to Neural Networks and Deep Learning and Basic Concepts research |
| 2 | Introduction to Neural Networks and Deep Learning and Basic Concepts | Introduction to Neural Networks and Deep Learning and Basic Concepts research |
| 3 | Training Neural Networks (Activation functions, dropout, batch normalisation) | Studying on training neural networks. |
| 4 | Optimisation Techniques for Deep Learning Models | Reading Optimisation Techniques for Deep Learning Models |
| 5 | Feedforward (deep) neural networks and training | Reading feedforward (deep) neural networks and training |
| 6 | Convolutional Neural Networks | research on Convolutional Neural Networks |
| 7 | Convolutional Neural Networks | research on Convolutional Neural Networks |
| 8 | Midterm exam | Preparing for midterm exam |
| 9 | Recursive Neural Networks (RNN, LSTM, GRU etc.) | Reading Recursive Neural Networks (RNN, LSTM, GRU etc.) |
| 10 | Recursive Neural Networks (RNN, LSTM, GRU etc.) | Reading Recursive Neural Networks (RNN, LSTM, GRU etc.) and implemantions |
| 11 | Hybrid Deep Learning Models | Reading Hybrid Deep Learning Models |
| 12 | Advanced/Selected Deep Learning Models | Reading Advanced/Selected Deep Learning Models |
| 13 | Advanced/Selected Deep Learning Models | Reading and Implementing Advanced/Selected Deep Learning Models |
| 14 | Project Presentations | Project presentations, reports and projects (codes) must be sent to course teacher before deadline (deadline will be announced). |
| 15 | Final project presentations | Preparing for final project presentations |