Attention Mechanism

1 post

Browse all articles with this tag

Mon Sep 01 2025

6401 words · 34 minutes

Deep Learning Notes-6: Transformer and Graph Neural Networks

Deep Learning Notes-6, covering the Transformer attention mechanism (self-attention, multi-head attention, positional encoding), language models (GPT/BERT), and graph neural networks (message passing, graph convolution, graph attention). Corresponds to Chapters 12-13 of "Deep Learning: Foundations and Concepts".

Notes Deep Learning Learning Transformer GNN Graph Neural Network Attention Mechanism