Trajectory Geometry of Transformer Representations Across Layers
Tracing the links between Statistical Mechanics and AI. Phase 1 features a vectorized 2D Ising Model simulation. Phase 2 maps these dynamics to Hopfield Networks to show how physical energy minimization drives memory recall.
Novel method for ID estimation based on FCI. Code related to the paper "Exploring neural manifolds across a wide range of intrinsic dimensions"
Hypothèse de la Cognition Géométrique. Cadre théorique unifiant l'intuition mathématique et la perception esthétique comme des processus de reconnaissance topologique dans des variétés neuronales de haute dimension.
Add a description, image, and links to the neural-manifolds topic page so that developers can more easily learn about it.
To associate your repository with the neural-manifolds topic, visit your repo's landing page and select "manage topics."