README.md

Winter-attention

This repository contains notes about attention mechanisms with code examples included

this repo have a inductive bias towards vision transformers * - *

Markdowns

• Introduction to Attention

• Why use Layer Normalization in Transformers?

Code Exploration

• Cosine Similarity and vector similarity

• Self-attention in MNIST

• Multi-head attention in MNIST

• How to use einsum

• How to use einops

Vision Transformers

• What is a Vision Transformer?

• Vision Transformer in pytorch from scratch

• Attention and positional encoding visualization