GPU Cluster for Neural PDEs and Neural Operators to Support MURI Research and Beyond

Abstract

The purpose of the present request is to acquire the latest GPUs that will enable us to train DeepOnet which is an emerging neural architecture based on neural operators and its variants at scale so that we can tackle diverse problems of interest to DoD, from hypersonics to materials and fracture, to optimizing path planning, and to developing a new suite of bio-inspired fast methods that will accelerate computational speeds in Scientific Machine Learning by a factor of 1,000.

Document Details

• Document Type: DoD Grant Award
• Publication Date: Mar 14, 2024
• Source ID: FA95502310671

Entities

People

• George Karniadakis

Organizations

• Air Force Office of Scientific Research
• Brown University
• United States Air Force

Tags

Fields of Study

• Computer science
• Physics

Readers

• Neuroscience
• Parallel and Distributed Computing.
• Research Science/Academic Research

Technology Areas

• AI & ML
• AI & ML - Autonomous Systems
• AI & ML - DoD AI Strategy
• AI & ML - Neural Networks
• Hypersonics