AITopics | physics-driven graph neural network

Collaborating Authors

physics-driven graph neural network

Information about AI from the News, Publications, and Conferences

Automatic Classification – Tagging and Summarization – Customizable Filtering and Analysis

If you are looking for an answer to the question What is Artificial Intelligence? and you only have a minute, then here's the definition the Association for the Advancement of Artificial Intelligence offers on its home page: "the scientific understanding of the mechanisms underlying thought and intelligent behavior and their embodiment in machines."

However, if you are fortunate enough to have more than a minute, then please get ready to embark upon an exciting journey exploring AI (but beware, it could last a lifetime) …

Supplemental Material for PhysGNN: A Physics-Driven Graph Neural Network Based Model for Predicting Soft Tissue Deformation in Image-Guided Neurosurgery

Neural Information Processing SystemsNov-17-2025, 15:09:58 GMT

The FE simulations in our study were carried out on quad-core Intel i7 @ 2.9 GHz CPU, while The summary table below compares our results with a few similar studies based on empirical grounds. Mesh Maximum Displacement in the Dataset(s) (mm) Mean Absolute Position Error (mm) Mean Euclidean Error (mm) % of Euclidean Error Below 1 mm Average of Maximum Euclidean Error per Simulation (mm) Tonutti et al. [2017] 1087 -- 0.191 0.18 -- --

artificial intelligence, machine learning, physics-driven graph neural network, (10 more...)

Neural Information Processing Systems

Country: