Generative AI 102

Description

Dive deeper into the world of Generative AI with this advanced course covering AutoEncoders, Variational AutoEncoders, Diffusion Models, and Transformers. Participants will explore the theory and practical applications of each model type, gaining insights into how modern generative systems are built and deployed.

Indicative Duration: 8 training hours
*Duration is adjusted based on the final scope and the target audience.

Scope

Learning Objectives

Upon completion of the course participants will be able to:

1. Understand the architecture and limitations of AutoEncoders in generative tasks.
2. Implement and evaluate Variational AutoEncoders (VAEs) for generative modeling.
3. Explain the theoretical foundations of Diffusion Models and their role in generative AI.
4. Describe how Transformers are trained for language modeling and how they generate text.
5. Compare different generative model families and their use cases in modern AI applications.

Target Audience

• Roles: Data Scientists, ML Engineers, AI Researchers, NLP Engineers
• Seniority Levels: Intermediate to Advanced professionals with prior exposure to generative modeling and deep learning

Prerequisite Knowledge

• Solid understanding of neural networks and backpropagation
• Familiarity with Keras or PyTorch
• Basic knowledge of generative models (e.g., GANs, AEs)
• Experience with Python and Jupyter notebooks
• Completion of Generative AI 101 or equivalent experience

Delivery Method

Sessions can be delivered via the following formats:

• Live Online – Interactive virtual sessions via video conferencing
• On-Site – At your organization’s premises
• In-Person – At Code.Hub’s training center
• Hybrid – A combination of online and in-person sessions

The training methodology combines presentations, live demonstrations, hands-on exercises and interactive discussions to ensure participants actively practice AI in realistic work scenarios.