Distributed parallel computing technique for EM modeling

This paper proposes a novel distributed parallel EM modeling technique to speed up the process of neural network modeling for EM structures. Existing techniques for EM modeling usually need to repeatedly change the parameters of microwave devices and drive the EM simulator to obtain sufficient training and testing samples. As the complexity in EM modeling problem increases, traditional techniques are computationally expensive on data generation and training due to the limited performance of a single computer. Our technique incorporates distributed parallel computing technique to neural network modeling. It generates data and trains neural network models in parallel using message passing interface (MPI). An example shows that our technique is much faster than traditional technique while maintaining good model accuracy.