TÜRKÇE
ENGLISH
Information
| Code | CENG0058 |
| Name | Applications of deep generative models |
| Term | 2024-2025 Academic Year |
| Term | Spring |
| Duration (T+A) | 3-0 (T-A) (17 Week) |
| ECTS | 6 ECTS |
| National Credit | 3 National Credit |
| Teaching Language | Türkçe |
| Level | Doktora Dersi |
| Type | Normal |
| Mode of study | Yüz Yüze Öğretim |
| Catalog Information Coordinator | Mehmet SARIGÜL |
| Course Instructor |
1 |
Course Goal / Objective
The goal of the Applications of Deep Generative Models course is to provide students with a comprehensive understanding of deep generative models and their diverse applications across various domains. The course aims to equip students with the knowledge and skills necessary to apply deep generative models to solve real-world problems, generate realistic synthetic data, and explore creative applications in areas such as computer vision, natural language processing, healthcare, and more.
Course Content
This course covers the Introduction to Deep Generative Models, Introduction to deep generative models, including Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and flow-based models, Applications of VAEs in image generation, image-to-image translation, and data synthesis, Generative Adversarial Networks (GANs), GAN architecture and training techniques, GAN evaluation metrics (e.g., inception score, Frechet Inception Distance), Applications of GANs in image generation, style transfer, and data augmentation, Flow-Based Generative Models, Architecture and training of flow-based models, Density estimation and likelihood evaluation, Applications of flow-based models in image generation and synthesis, Text Generation and Language Modeling, Recurrent Neural Networks (RNNs) and LSTM models for language modeling, Applications of deep generative models in text generation, dialogue systems, and language translation, Unsupervised and Semi-supervised Learning, Anomaly Detection and Outlier Analysis, Applications in fraud detection, cybersecurity, and outlier analysis, Data Augmentation and Privacy, Healthcare and Medical Image Analysis, Artistic image generation using deep generative models, Ethical Considerations and Social Impact Advanced Topics and Recent Advancements.
Course Precondition
Knowledge of basic programming, linear algebra, and probability theory.
Resources
Tomczak, J. M. (2022). Deep generative modeling (pp. 1-197). Springer.
Notes
Tomczak, J. M. (2022). Deep generative modeling (pp. 1-197). Springer.
Course Learning Outcomes
| Order | Course Learning Outcomes |
|---|---|
| LO01 | Understanding of Deep Generative Models |
| LO02 | Knowledge of Generative Model Applications |
| LO03 | Implementation skill for Domain-Specific Applications of Deep Generative Models |
| LO04 | Evaluation and Assessment for Deep Learning Applications |
Relation with Program Learning Outcome
| Order | Type | Program Learning Outcomes | Level |
|---|---|---|---|
| PLO01 | Bilgi - Kuramsal, Olgusal | On the basis of the competencies gained at the undergraduate level, it has an advanced level of knowledge and understanding that provides the basis for original studies in the field of Computer Engineering. | 4 |
| PLO02 | Bilgi - Kuramsal, Olgusal | By reaching scientific knowledge in the field of engineering, he/she reaches the knowledge in depth and depth, evaluates, interprets and applies the information. | 4 |
| PLO03 | Yetkinlikler - Öğrenme Yetkinliği | Being aware of the new and developing practices of his / her profession and examining and learning when necessary. | 3 |
| PLO04 | Yetkinlikler - Öğrenme Yetkinliği | Constructs engineering problems, develops methods to solve them and applies innovative methods in solutions. | 3 |
| PLO05 | Yetkinlikler - Öğrenme Yetkinliği | Designs and applies analytical, modeling and experimental based researches, analyzes and interprets complex situations encountered in this process. | 2 |
| PLO06 | Yetkinlikler - Öğrenme Yetkinliği | Develops new and / or original ideas and methods, develops innovative solutions in system, part or process design. | 2 |
| PLO07 | Beceriler - Bilişsel, Uygulamalı | Has the skills of learning. | 2 |
| PLO08 | Beceriler - Bilişsel, Uygulamalı | Being aware of new and emerging applications of Computer Engineering examines and learns them if necessary. | 3 |
| PLO09 | Beceriler - Bilişsel, Uygulamalı | Transmits the processes and results of their studies in written or oral form in the national and international environments outside or outside the field of Computer Engineering. | |
| PLO10 | Beceriler - Bilişsel, Uygulamalı | Has comprehensive knowledge about current techniques and methods and their limitations in Computer Engineering. | 1 |
| PLO11 | Beceriler - Bilişsel, Uygulamalı | Uses information and communication technologies at an advanced level interactively with computer software required by Computer Engineering. | 1 |
| PLO12 | Bilgi - Kuramsal, Olgusal | Observes social, scientific and ethical values in all professional activities. | 2 |
Week Plan
| Week | Topic | Preparation | Methods |
|---|---|---|---|
| 1 | Introduction to deep generative models and their applications. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 2 | Variational Autoencoders (VAEs): architecture, training, and applications. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 3 | Generative Adversarial Networks (GANs): architecture, training, and applications. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 4 | Flow-based generative models: architecture, training, and applications. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 5 | Image generation and synthesis using deep generative models. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 6 | Text generation and language modeling with deep generative models. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 7 | Unsupervised and semi-supervised learning using generative models. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 8 | Mid-Term Exam | Ölçme Yöntemleri: Yazılı Sınav |
|
| 9 | Evaluation metrics for generative models: inception score, FID, etc. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 10 | Anomaly detection and outlier analysis with generative models. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 11 | Data augmentation using generative models. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 12 | Privacy considerations and adversarial attacks on generative models. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 13 | Healthcare and medical image analysis applications. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 14 | Creative applications of generative models: art, music, design. | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 15 | Review | Reading the lecture notes | Öğretim Yöntemleri: Anlatım |
| 16 | Term Exams | Ölçme Yöntemleri: Yazılı Sınav |
|
| 17 | Term Exams | Ölçme Yöntemleri: Yazılı Sınav |
Student Workload - ECTS
| Works | Number | Time (Hour) | Workload (Hour) |
|---|---|---|---|
| Course Related Works | |||
| Class Time (Exam weeks are excluded) | 14 | 3 | 42 |
| Out of Class Study (Preliminary Work, Practice) | 14 | 5 | 70 |
| Assesment Related Works | |||
| Homeworks, Projects, Others | 0 | 0 | 0 |
| Mid-term Exams (Written, Oral, etc.) | 1 | 14 | 14 |
| Final Exam | 1 | 28 | 28 |
| Total Workload (Hour) | 154 | ||
| Total Workload / 25 (h) | 6,16 | ||
| ECTS | 6 ECTS | ||