Výsledky vyhledávání

Report

Towards Compositional Interpretability for XAI

Autor: Tull, Sean, Lorenz, Robin, Clark, Stephen, Khan, Ilyas, Coecke, Bob

Artificial intelligence (AI) is currently based largely on black-box machine learning models which lack interpretability. The field of eXplainable AI (XAI) strives to address this major concern, being critical in high-stakes areas such as the finance

Externí odkaz: http://arxiv.org/abs/2406.17583

Zobrazit plný text záznamu

Report

Uniqueness of Asymptotically Conical Gradient Shrinking Solitons in G_2-Laplacian Flow

Autor: Haskins, Mark, Khan, Ilyas, Payne, Alec

We prove a uniqueness result for asymptotically conical (AC) gradient shrinking solitons for the Laplacian flow of closed G_2-structures: If two gradient shrinking solitons to Laplacian flow are asymptotic to the same closed G_2-cone, then their G_2-

Externí odkaz: http://arxiv.org/abs/2210.07954

Zobrazit plný text záznamu

Report

Nonconvex ancient solutions to Curve Shortening Flow

Autor: Zhang, Yongzhe, Olson, Connor, Khan, Ilyas, Angenent, Sigurd

We construct an ancient solution to planar curve shortening. The solution is at all times compact and embedded. For $t\ll0$ it is approximated by the rotating Yin-Yang soliton, truncated at a finite angle $\alpha(t) = -t$, and closed off by a small c

Externí odkaz: http://arxiv.org/abs/2204.05253

Zobrazit plný text záznamu