Litcius/Paper detail

When and why PINNs fail to train: A neural tangent kernel perspective

Sifan Wang, Xinling Yu, Paris Perdikaris

2021Journal of Computational Physics1,184 citationsDOIOpen Access PDF

Topics & Concepts

Gradient descentArtificial neural networkComputer scienceTangentLimit (mathematics)AlgorithmApplied mathematicsKernel (algebra)Convergence (economics)MathematicsMathematical optimizationArtificial intelligenceMathematical analysisGeometryDiscrete mathematicsEconomic growthEconomicsModel Reduction and Neural NetworksNuclear reactor physics and engineeringProbabilistic and Robust Engineering Design