Guardado en:
Detalles Bibliográficos
Autores principales: Lindsay, Audrey, Ruehle, Fabian
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2502.12243
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913695506890752
author Lindsay, Audrey
Ruehle, Fabian
author_facet Lindsay, Audrey
Ruehle, Fabian
contents We analyze different aspects of neural network predictions of knot invariants. First, we investigate the impact of different knot representations on the prediction of invariants and find that braid representations work in general the best. Second, we study which knot invariants are easy to learn, with invariants derived from hyperbolic geometry and knot diagrams being very easy to learn, while invariants derived from topological or homological data are harder. Predicting the Arf invariant could not be learned for any representation. Third, we propose a cosine similarity score based on gradient saliency vectors, and a joint misclassification score to uncover similarities in neural networks trained to predict related topological invariants.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12243
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle On the Learnability of Knot Invariants: Representation, Predictability, and Neural Similarity
Lindsay, Audrey
Ruehle, Fabian
Geometric Topology
Machine Learning
We analyze different aspects of neural network predictions of knot invariants. First, we investigate the impact of different knot representations on the prediction of invariants and find that braid representations work in general the best. Second, we study which knot invariants are easy to learn, with invariants derived from hyperbolic geometry and knot diagrams being very easy to learn, while invariants derived from topological or homological data are harder. Predicting the Arf invariant could not be learned for any representation. Third, we propose a cosine similarity score based on gradient saliency vectors, and a joint misclassification score to uncover similarities in neural networks trained to predict related topological invariants.
title On the Learnability of Knot Invariants: Representation, Predictability, and Neural Similarity
topic Geometric Topology
Machine Learning
url https://arxiv.org/abs/2502.12243