Intuition Behind Self-Attention Mechanism in Transformer Networks

This is the first part of the Transformer Series. Here, I present an intuitive understanding of the self-attention mechanism in transformer networks.


[Paper] Attention Is All You Need: papers.nips.cc/paper/7181-attention-is-all-you-nee…


Other Resources:
Video Lecture on Word2Vec:    • Lecture 2 | Word Vector Representations: w...  
Great article on Word2Vec: jalammar.github.io/illustrated-word2vec/