Description: Transformers fundamentally changed AI by efficiently capturing long-range dependencies in data, moving beyond simple word-to-word learning to understand true context, making advanced AI possible. AI transformer models serve as the foundation for many AI applications, such as large language models (LLMs), generative pretrained transformers (GPTs), virtual assistants. Application development currently builds on existing AI transformers, which are often treated as “black boxes”. This seminar aims to provide a deeper understanding into AI transformers by opening up and delving inside the box. The goal is to better understand the underlying principles and gain insights into how a transformer arrives at it output.

CUI