Introduction
Generative AI enables machines to create new content such as text, images, music, and code. This course explores the fundamentals behind generative models and their applications in creative and productive tasks. Participants will learn how models like GANs and transformers generate realistic outputs. Real-world case studies will highlight how organizations utilize generative AI responsibly. By the end, learners will have a practical understanding of implementing generative solutions.
Course Objectives
- Understand how generative models work
- Explore popular generative architectures
- Create basic generative outputs
- Learn evaluation techniques for generative models
- Examine ethical considerations in content creation
Target Audience
- Developers and ML engineers
- Creative professionals
- Data scientists exploring generative AI
- Students studying deep learning
- Innovation teams building AI-powered tools
Course Outline
- 5 Sections
- 0 Lessons
- 5 Days
Expand all sectionsCollapse all sections
- Day 1: Introduction to Generative Models• What is generative AI?
• Generative vs. discriminative models
• Data distributions
• Modern use cases
• Hands-on: Simple generation tasks0 - Day 2: Variational Autoencoders (VAEs)• Encoder–decoder structure
• Latent space concepts
• Loss functions
• Applications
• Hands-on: Train a VAE0 - Day 3: Generative Adversarial Networks (GANs)• Generator and discriminator
• Training challenges
• Popular GAN variants
• Evaluating GAN outputs
• Hands-on: Train a simple GAN0 - Day 4: Transformers & Large Models• Self-attention
• Large language models
• Image and text generation
• Scaling laws
• Hands-on: Use a pre-trained LLM0 - Day 5: Practical Applications & Ethics• Synthetic images and text
• Creative industry use cases
• Legal risks of generated content
• Bias and safety in generative models
• Capstone project0
Instructor
Lessons:
