Skip to main content
Patrick Colm Audley

Patrick Colm Audley

Hacker · Full-Spectrum Technologist · Polymath

Notes

Short essays, cross-posts, and technical notes.

  1. Standard Graph Neural Networks need curved semantic manifolds

    Standard GNNs are structurally constrained when mapping complex text attribution; linear aggregation in flat Euclidean space inevitably forces semantic drift. Looking to connect with researchers in TDA, geometric deep learning, and spectral graph theory.