In this module, you'll learn:
  • What is the Attention Mechanism
  • What are Transformers
  • The variations of the Attention Mechanism (Self-Attention, Cross-Attention, ...)
  • The difference between a Vision Transformer and a regular Transformer
  • Why Transformers have the potential to replace Convolutions in Computer Vision
  • What are Query, Key, and Values in Attention
  • How Multi-Head Attention works