Deflation-PINNs: Learning Multiple Solutions for PDEs and Landau-de Gennes
Deflation-PINNs: 学习PDEs和Landau-de Gennes的多个解
机构 * Department of Mathematics, Indian Institute of Science, Bangalore(印度科学研究所数学系,班加罗尔) ; Department of Computing and Mathematical Sciences, California Institute of Technology(加州理工学院计算与数学科学系)
AI总结 本文提出Deflation-PINNs,通过引入消元损失和基于PINNs与DeepONets的架构,解决PDEs多解识别问题,并在液态晶体Landau-de Gennes模型中验证了其有效性。