Tagged
Graph Neural Networks
Essence of Linear Algebra (18): Frontiers and Summary
Series finale: quantum gates as unitary matrices, graph convolution as Laplacian filtering, attention as soft retrieval, LoRA as low-rank adaptation, tensor networks, the matrix exponential, free probability, and a …
PDE and Machine Learning (8): Reaction-Diffusion Systems and Graph Neural Networks
Deep GNNs collapse because they are diffusion equations on graphs. Turing's reaction-diffusion theory tells us how to fix it -- and closes the eight-chapter PDE+ML series.