Full Course Title: Generative AI Instructional Hours (Contact Hours): 60
Learning Activities:
☒ Class Discussions/Discussion Boards ☒ Student Projects
☒ Peer-to-Peer Work (pairs, small groups) ☒ Readings
☒ Written Assignments (reports, essays) ☒ Textbook/Workbook Exercises
☒ Case Study Analysis ☐ Other: Click to enter
Methods of Assessment/Grading Criteria:
☒ Class/Discussion Boards Participation ☒ Individual Projects/Presentations
☒ Written Assignments (reports, essays) ☒ Group Projects/Presentations
☒ Exams/Quizzes ☐ Other: Click to enter
Course Description
This course provides an in-depth understanding of Generative AI, including its theoretical
foundations, practical applications, and ethical considerations. Students will learn about various
generative models such as Generative Adversarial Networks (GANs), Variational Autoencoders
(VAEs), and Transformer-based models. The course includes hands-on projects and practical
exercises to reinforce the concepts learned.
Learning Outcomes
By the end of this course, students will be able to:
1. Understand the theoretical foundations of generative models.
2. Implement and fine-tune various generative models using modern AI frameworks.
3. Evaluate the performance of generative models using appropriate metrics.
4. Apply generative models to real-world problems such as image generation, text
generation, and data augmentation.
5. Understand and address ethical considerations related to Generative AI.
6. Develop innovative applications leveraging Generative AI techniques.
Method of Assessment
● Assignments (30%): Regular assignments to reinforce theoretical concepts and practical
skills.
● Projects (40%): Two major projects where students design, implement, and present a
generative AI application.
● Quizzes (10%): Periodic quizzes to assess understanding of key concepts.
● Final Exam (20%): Comprehensive exam covering all course topics.
Course Topics
1. Introduction to Generative AI
o Overview of AI and Machine Learning
o History and evolution of Generative AI
o Applications of Generative AI
2. Fundamentals of Generative Models
o Probability distributions and sampling
o Introduction to neural networks and deep learning
o Generative vs. discriminative models
3. Generative Adversarial Networks (GANs)
o Architecture and components of GANs
o Training GANs and addressing common challenges
o Variants of GANs (DCGAN, CycleGAN, StyleGAN)
4. Variational Autoencoders (VAEs)
o Theoretical foundations of VAEs
o Implementing VAEs and understanding latent space
o Applications of VAEs
5. Transformer-based Models
o Introduction to transformers and self-attention mechanism
o BERT, GPT, and other transformer models
o Applications in text and image generation
6. Advanced Topics in Generative AI
o Conditional generative models
o Sequence generation and autoregressive models
o Transfer learning and fine-tuning for specific tasks
7. Capstone Project
o Project design and proposal
o Implementation and testing
o Presentation and peer review
Prerequisites
To enroll in this course, students should have:
● Basic knowledge of Python programming
● Understanding of fundamental machine learning concepts
● Experience with deep learning frameworks (TensorFlow or PyTorch)
● Familiarity with basic statistics and probability
This curriculum provides a comprehensive guide to learning Generative AI, balancing theoretical
knowledge with practical skills and ethical considerations.
