|
|
| ISTL5061 | Deep Learning | 3+0+0 | ECTS:7.5 | | Year / Semester | Fall Semester | | Level of Course | Third Cycle | | Status | Elective | | Department | DEPARTMENT of STATISTICS and COMPUTER SCIENCES | | Prerequisites and co-requisites | None | | Mode of Delivery | | | Contact Hours | 14 weeks - 3 hours of lectures per week | | Lecturer | Dr. Öğr. Üyesi Uğur ŞEVİK | | Co-Lecturer | Asst. Prof. Uğur ŞEVİK | | Language of instruction | Turkish | | Professional practise ( internship ) | None | | | | The aim of the course: | | The aim of this course is to provide students with advanced knowledge and skills in the field of deep learning. Students are expected to understand, apply, and optimize deep learning models. The course aims to develop students' ability to select appropriate deep learning techniques for various data types and application areas and to use these techniques effectively. As a result, students will be equipped to conduct independent research and generate innovative solutions in the field of deep learning. |
| Programme Outcomes | CTPO | TOA | | Upon successful completion of the course, the students will be able to : | | | | PO - 1 : | Ability to understand the theoretical foundations and structures of deep learning models. | 2,3 | 1,3,6, | | PO - 2 : | Skill in applying deep learning algorithms and techniques. | 2,3 | 1,3,6, | | PO - 3 : | Competence in selecting and utilizing appropriate deep learning methods for various data types and application areas. | 2,3 | 1,3,6, | | PO - 4 : | Capacity to design, implement, and evaluate deep learning projects. | 2,3 | 1,3,6, | | 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), PO : Learning Outcome | | |
| This course covers advanced topics in artificial intelligence and machine learning. The course addresses the theoretical foundations, structures, and training processes of deep learning models. Key techniques such as convolutional neural networks (CNN), backpropagation, recurrent neural networks (RNN), natural language processing (NLP), generative adversarial networks (GAN), and deep reinforcement learning will be emphasized. Additionally, practical examples and projects concerning the use of these methods in various application domains will be included. |
| |
| Course Syllabus | | Week | Subject | Related Notes / Files | | Week 1 | Introduction to Deep Learning - Foundations and history of deep learning | | | Week 2 | Fundamentals of Artificial Neural Networks - Perceptron, multi-layer perceptron (MLP) | | | Week 3 | Backpropagation and Optimization Techniques Backpropagation algorithm and optimization methods | | | Week 4 | Convolutional Neural Networks (CNN) Structure and applications of CNN | | | Week 5 | Recurrent Neural Networks (RNN) Structure of RNN, LSTM and GRU cells | | | Week 6 | Natural Language Processing (NLP) NLP techniques and deep learning applications | | | Week 7 | Generative Adversarial Networks (GAN) Structure and applications of GAN | | | Week 8 | Deep Reinforcement Learning Reinforcement learning and its applications | | | Week 9 | Midterm Exam | | | Week 10 | Data Preparation for Deep Learning Data preprocessing and augmentation techniques | | | Week 11 | Model Evaluation and Error Analysis Model performance metrics and error analysis | | | Week 12 | Transfer Learning and Fine-Tuning Transfer learning techniques and fine-tuning methods | | | Week 13 | Deep Learning Projects and Applications Application areas and example projects | | | Week 14 | Large-Scale Deep Learning Big data and distributed deep learning | | | Week 15 | Assignment Presentations | | | Week 16 | Final Exam | | | |
| 1 | Ian Goodfellow, Yoshua Bengio, Aaron Courville, 2018, Derin Öğrenme, Buzdağı Yayınları, . | | | |
| 1 | Jon Krohn, Grant Beyleveld, Aglaé Bassens, 2019, Deep Learning Illustrated: A Visual, Interactive Guide to Artificial Intelligence, Addison-Wesley Professional, | | | 2 | Magnus Ekman, 2021, Learning Deep Learning: Theory and Practice of Neural Networks, Computer Vision, NLP, and Transformers using TensorFlow, Addison-Wesley Professional, | | | |
| Method of Assessment | | Type of assessment | Week No | Date | Duration (hours) | Weight (%) | | | | | | | | |
| 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 | 14 | 42 | | Arasınav için hazırlık | 20 | 1 | 20 | | Arasınav | 2 | 1 | 2 | | Ödev | 1 | 6 | 6 | | Dönem sonu sınavı için hazırlık | 20 | 1 | 20 | | Dönem sonu sınavı | 2 | 1 | 2 | | Total work load | | | 92 |
|