A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
This paper provides a numerical analysis of physics-informed neural networks and related models, focusing on their accuracy and convergence for solving forward and inverse problems.
Unknown
This paper provides a comprehensive review of Physics-informed neural networks (PINNs), covering methodologies, applications, and challenges in solving PDE problems.
Unknown
This paper introduces self-adaptive physics-informed neural networks that dynamically adjust loss weights during training to improve solution accuracy for nonlinear PDEs.
Unknown
This paper identifies and addresses gradient pathologies in physics-informed neural networks, where loss terms of different nature cause training difficulties, and proposes mitigation strategies.
Unknown
This paper characterizes possible failure modes in physics-informed neural networks (PINNs), identifying causes and proposing mitigation strategies.
Unknown
This paper introduces fPINNs, a physics-informed neural network framework for solving fractional partial differential equations by incorporating fractional derivatives into the loss function.
Unknown
This paper explores the application of physics-informed neural networks (PINNs) to heat transfer problems, demonstrating their effectiveness in solving realistic scenarios with noisy data.
Unknown
This paper provides a comprehensive review of physics-informed neural networks, covering techniques, applications, trends, and challenges.
Sifan Wang, Shyam Sankaran, Hanwen Wang, et al.
This paper provides a comprehensive expert guide to training physics-informed neural networks, offering practical strategies and best practices to overcome common challenges.
Unknown
This review surveys the landscape of physics-informed neural networks (PINNs), from the vanilla formulation to a broader range of collocation-based variants, and discusses current challenges and future directions.