##  [Attention Is All You Need](https://arxiv.org/pdf/1706.03762.pdf) ... but scarcity of attention drives Internet world



-  https://wiki.pathmind.com/attention-mechanism-memory-network

[Intro to Attention](https://knowen-production.s3.amazonaws.com/uploads/attachment/file/4962/intro%2Bto%2Battention.pdf)

https://machinelearningmastery.com/how-does-attention-work-in-encoder-decoder-recurrent-neural-networks/

> The basic idea is to read the input structure twice: once to encode the gist and another time (at each step while decoding) to "pay attention" to certain details.

[Attention mechanism](https://knowen-production.s3.amazonaws.com/uploads/attachment/file/4972/attention%2Bmechanism.pdf)