all AI news
Uncertainty Quantification of Graph Convolution Neural Network Models of Evolving Processes
Feb. 20, 2024, 5:41 a.m. | Jeremiah Hauth, Cosmin Safta, Xun Huan, Ravi G. Patel, Reese E. Jones
cs.LG updates on arXiv.org arxiv.org
Abstract: The application of neural network models to scientific machine learning tasks has proliferated in recent years. In particular, neural network models have proved to be adept at modeling processes with spatial-temporal complexity. Nevertheless, these highly parameterized models have garnered skepticism in their ability to produce outputs with quantified error bounds over the regimes of interest. Hence there is a need to find uncertainty quantification methods that are suitable for neural networks. In this work we …
abstract adept application arxiv complexity convolution convolution neural network cs.lg graph machine machine learning math.st modeling network neural network physics.comp-ph processes quantification skepticism spatial stat.th tasks temporal type uncertainty
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US