Inverse problem;
memory term;
optimization;
deep learning;
IDENTIFICATION;
KERNEL;
D O I:
暂无
中图分类号:
O29 [应用数学];
学科分类号:
070104 ;
摘要:
Our goal of this paper is the identification of an initial condition in a heat equation that contains a memory term from final data. To this aim, we first establish the well-posedness of the direct problem. Then we prove the continuity and the G -derivability of the cost function. Finally, we validate the results numerically by using a deep neural network. Our algorithm is meshfree.