ISTINYE UNIVERSITY BİLGİ PAKETİ / DERS KATALOĞU
| Data Science (Master) (with Thesis) (English) | |||||
| Master | TR-NQF-HE: Level 7 | QF-EHEA: Second Cycle | EQF-LLL: Level 7 | ||
Course Introduction and Application Information
| Course Code: | DATS5005 | ||||
| Course Name: | Deep Learning | ||||
| Semester: | Spring | ||||
| Course Credits: |
|
||||
| Language of instruction: | English | ||||
| Course Condition: | |||||
| Does the Course Require Work Experience?: | No | ||||
| Type of course: | Departmental Elective | ||||
| Course Level: |
|
||||
| Mode of Delivery: | E-Learning | ||||
| Course Coordinator: | Araş. Gör. KAZIM TİMUÇİN UTKAN | ||||
| Course Lecturer(s): | |||||
| Course Assistants: |
Course Objective and Content
| Course Objectives: | The main objective of this deep learning course is to provide students with advanced knowledge and skills in deep learning theory and algorithms as well as their practical applications. We aim to develop a comprehensive understanding of the mathematical underpinnings of deep learning, different deep learning models, network architectures and how these models can be applied to real-world problems. Furthermore, upon graduation, students are expected to have the capacity to analyze academic or industrial problems and generate stable deep learning solutions. |
| Course Content: | 1. Mathematical foundations and basic concepts of deep learning. 2. Multilayer perceptrons, hyperparameter optimization, and feed-forward networks. 3. Convolutional neural networks and their applications to image processing. 4. Backpropagation algorithm, optimization methods and weighting updates. 5. Long Short Term Memory (LSTM) and recurrent neural networks (RNNs); studies on sequence data. |
Learning Outcomes
|
The students who have succeeded in this course;
1) - Gain the ability to explain deep learning theories and basic concepts. 2) - Ability to build and train deep network architectures. 3) - Develop the ability to apply advanced deep learning algorithms on real-world data sets. 4) - Gain the ability to analyze and improve the performance of deep learning models. 5) - To have the knowledge to develop and apply deep learning models for different problems. |
Course Flow Plan
| Week | Subject | Related Preparation |
| 1) | Course Introduction - Overview and history of Deep Learning. | - |
| 2) | Mathematical Foundations - Linear Algebra, Calculus, and Probability Theory. | - |
| 3) | Basic Neural Networks - Perceptrons, MLPs, and Feedforward Networks. | - |
| 4) | Backpropagation - Gradient Descent, Stochastic Gradient Descent, and Variants. | - |
| 5) | Optimization and Regularization Techniques - Overfitting, Dropout, and Batch Normalization. | - |
| 6) | Deep Feedforward Networks - Activation Functions, Weight Initialization, and Troubleshooting. | - |
| 7) | CNNs - Architecture, Pooling Layers, and Case Studies in Image Recognition. | - |
| 8) | Midterm Exam. | - |
| 9) | RNNs and LSTMs - Unfolding in Time, Memory Mechanisms, and Applications. | - |
| 10) | Embeddings and Sequence-to-Sequence Models - Word Embeddings and Encoder-Decoder Architecture. | |
| 11) | Transfer Learning and Fine-Tuning - Pretrained Models and Adaptation to New Tasks. | |
| 12) | Generative Models, Architectural Innovations, and Training Strategies. | |
| 13) | Reinforcement Learning Basics - Markov Decision Processes, Q-Learning, and Policy Gradients. | |
| 14) | Attention Mechanisms and Transformers - From RNNs to Self-Attention and Beyond. | |
| 15) | Ethical Considerations and Future of Deep Learning - Bias, Fairness, and Interpretability. | |
| 16) | Final Exam. | - |
Sources
| Course Notes / Textbooks: | Deep Learning with Python |
| References: | Deep Learning with Python |
Course - Program Learning Outcome Relationship
| Course Learning Outcomes | 1 |
2 |
3 |
4 |
5 |
|---|---|---|---|---|---|
| Program Outcomes | |||||
| 1) Students who successfully complete this program, Knows the scope of technical applications of data science and the tools that can be used. | 3 | 2 | 3 | 3 | 3 |
| 2) Students who successfully complete this program, Knows the effects of application results on society-culture-law. | 2 | 3 | 2 | 3 | 2 |
| 3) Students who complete this program; Recognize the mathematics and code in application processes | 2 | 2 | 2 | 2 | 2 |
| 4) Students who complete this program; Explain the effects of the processes in data science on the output and the individual | 2 | 2 | 2 | 2 | 3 |
| 5) Students who successfully complete this program, Understands the insight-foresight and foresight created by data science as a whole in the face of a certain discipline/case. | 3 | 3 | 2 | 3 | 2 |
Course - Learning Outcome Relationship
| No Effect | 1 Lowest | 2 Average | 3 Highest |
| Program Outcomes | Level of Contribution | |
| 1) | Students who successfully complete this program, Knows the scope of technical applications of data science and the tools that can be used. | 2 |
| 2) | Students who successfully complete this program, Knows the effects of application results on society-culture-law. | 2 |
| 3) | Students who complete this program; Recognize the mathematics and code in application processes | 3 |
| 4) | Students who complete this program; Explain the effects of the processes in data science on the output and the individual | 3 |
| 5) | Students who successfully complete this program, Understands the insight-foresight and foresight created by data science as a whole in the face of a certain discipline/case. | 2 |
Assessment & Grading
| Semester Requirements | Number of Activities | Level of Contribution |
| Midterms | 1 | % 40 |
| Final | 1 | % 60 |
| total | % 100 | |
| PERCENTAGE OF SEMESTER WORK | % 40 | |
| PERCENTAGE OF FINAL WORK | % 60 | |
| total | % 100 | |
Workload and ECTS Credit Calculation
| Activities | Number of Activities | Workload |
| Course Hours | 14 | 42 |
| Midterms | 8 | 29 |
| Final | 8 | 78 |
| Total Workload | 149 | |