Visual Guide to Transformer Neural Networks (Series) - Step by Step Intuitive Explanation

Episode 0 - [OPTIONAL] The Neuroscience of "Attention"
[ Ссылка ]

Episode 1 - Position Embeddings
[ Ссылка ]

Episode 2 - Multi-Head & Self-Attention
[ Ссылка ]

Episode 3 - Decoder’s Masked Attention
[ Ссылка ]

This video series explains the math, as well as the intuition behind the Transformer Neural Networks that were first introduced by the “Attention is All You Need” paper.

--------------------------------------------------------------
References and Other Great Resources
--------------------------------------------------------------

Attention is All You Need
[ Ссылка ]

Jay Alammar – The Illustrated Transformer
[ Ссылка ]...

The A.I Hacker – Illustrated Guide to Transformers Neural Networks: A step by step explanation
[ Ссылка ]...

Amirhoussein Kazemnejad Blog Post - Transformer Architecture: The Positional Encoding
[ Ссылка ]...

Yannic Kilcher Youtube Video – Attention is All You Need
[ Ссылка ]...

свернуть