Neural network application to solve Fredholm integral equations ofthe first kind

摘要

Summary form only given, as follows. Inverse problems appear oftennin many fields of science and engineering. The authors applied thenneural network to obtain the numerical solution of Fredholm integralnequations of the first kind, which defines a typical inverse problem.nUnder some a priori information on the relevant system, the network isnable to learn an inverse mapping from an output function to an inputnfunction of the integral equations. It is shown by two examples thatnthese inverse mappings are numerically stable and robust for the noisyninput data