Search Results - paris+perdikaris

1 Results Sort By:
PirateNets: Efficient, Scalable, And Robust Neural Network Architecture For Physics-Informed Deep Learning
Physics-Informed Residual Adaptive Networks (PirateNets) is a neural network architecture designed to enable efficient and stable training of deep Physics-Informed Neural Networks (PINNs). Problem: Machine learning plays a key role in advancing science by analyzing complex data, building predictive models, and uncovering nonlinear relationships. Physics-Informed...
Published: 11/25/2025   |   Inventor(s): Paris Perdikaris, Sifan Wang
Keywords(s): Artificial Intelligence (AI) & Machine Learning, Software
Category(s): Technology Classifications > Computer Information Systems