AI RESEARCH
Transferable Physics-Informed Representations via Closed-Form Head Adaptation
arXiv CS.LG
•
ArXi:2604.21761v1 Announce Type: new Physics-informed neural networks (PINNs) have garnered significant interest for their potential in solving partial differential equations (PDEs) that govern a wide range of physical phenomena. By incorporating physical laws into the learning process, PINN models have nstrated the ability to examples, indicating they do not generalize well to unseen problem instances. In this paper, we present a transferable learning approach for PINNs premised on a fast Pseudoinverse PINN framework (Pi.