|
|
| YZT2005 | Artificial Neural Networks and Deep Learning | 3+0+0 | ECTS:5 | | Year / Semester | Fall Semester | | Level of Course | Short Cycle | | Status | Compulsory | | Department | Computer Technology | | Prerequisites and co-requisites | None | | Mode of Delivery | | | Contact Hours | 14 weeks - 3 hours of lectures per week | | Lecturer | Öğr. Gör. Elif ARAS | | Co-Lecturer | | | Language of instruction | Turkish | | Professional practise ( internship ) | None | | | | The aim of the course: | | The course aims to teach the fundamental concepts, working principles, and application areas of artificial neural networks and deep learning methods. It is designed to enable students to understand and utilize advanced algorithms to solve artificial intelligence and machine learning problems. Additionally, the course focuses on topics such as neural network architectures, training processes, and optimization techniques, aiming to develop practical skills alongside theoretical knowledge through hands-on projects. |
| Learning Outcomes | CTPO | TOA | | Upon successful completion of the course, the students will be able to : | | | | LO - 1 : | Proficiency in Convolutional Neural Networks (CNNs)
| 1,3,4,5 | 1,3, | | LO - 2 : | Proficiency in TensorFlow and PyTorch | 1,2,3,7 | | | LO - 3 : | Training Neural Networks | 1,2,3,7 | | | LO - 4 : | Measures Against Overfitting | 1,2,3,7 | | | LO - 5 : | Gaining Practical Experience in Deep Learning Models
| 1,2,3,7 | | | CTPO : Contribution to programme outcomes, TOA :Type of assessment (1: written exam, 2: Oral exam, 3: Homework assignment, 4: Laboratory exercise/exam, 5: Seminar / presentation, 6: Term paper), LO : Learning Outcome | | |
| The basic architecture and components of neural networks, the role of activation functions in neural networks, and convolutional neural networks (CNNs) along with their applications in image processing. |
| |
| Course Syllabus | | Week | Subject | Related Notes / Files | | Week 1 | Introduction to Neural Networks | | | Week 2 | Perceptrons and Linear Separability | | | Week 3 | Activation Functions | | | Week 4 | Feedforward Neural Networks
| | | Week 5 | Backpropagation Algorithm
| | | Week 6 | Gradient Descent Optimization
| | | Week 7 | Regularization Techniques: L1 and L2 Regularization, Dropout Regularization
| | | Week 8 | Convolutional Neural Networks (CNNs)
| | | Week 9 | Midterm Exam | | | Week 10 | Image Classification with CNNs
| | | Week 11 | Transfer Learning
| | | Week 12 | Recurrent Neural Networks (RNNs)
| | | Week 13 | Sequence-to-Sequence Models
| | | Week 14 | Overview of Deep Learning Frameworks | | | Week 15 | TensorFlow or PyTorch | | | Week 16 | Final Exam | | | |
| Method of Assessment | | Type of assessment | Week No | Date | Duration (hours) | Weight (%) | | Mid-term exam | 9 | | 1 | 50 | | End-of-term exam | 16 | | 1 | 50 | | |
| Student Work Load and its Distribution | | Type of work | Duration (hours pw) | No of weeks / Number of activity | Hours in total per term | | Yüz yüze eğitim | 3 | 15 | 45 | | Sınıf dışı çalışma | 2 | 15 | 30 | | Arasınav için hazırlık | 1 | 9 | 9 | | Arasınav | 1 | 1 | 1 | | Ödev | 2 | 10 | 20 | | Dönem sonu sınavı için hazırlık | 1 | 15 | 15 | | Dönem sonu sınavı | 1 | 1 | 1 | | Total work load | | | 121 |
|