- In this paper, we face an electromagnetic inverse problem by exploiting Neural Networks (NNs). In particular, we tackle an inverse source problem and propose an iterative pruning scheme based on the use of the Singular Value Decomposition (SVD) of weight matrices and bias vectors associated to each layer to reduce the NN complexity. The performance of the approach is shown numerically.
A Neural Network Approach for the Solution of an Electromagnetic Inverse Source Problem with SVD-based Pruning / Capozzoli, A.; Curcio, C.; Liseno, A.. - 2024(2024), pp. 147-151. ( 13th IEEE-APS Topical Conference on Antennas and Propagation in Wireless Communications, APWC 2024 Altis Grand Hotel, Rua Castilho 11, prt 2024) [10.1109/APWC61918.2024.10701760].
A Neural Network Approach for the Solution of an Electromagnetic Inverse Source Problem with SVD-based Pruning
Capozzoli A.;Curcio C.;Liseno A.
2024
Abstract
- In this paper, we face an electromagnetic inverse problem by exploiting Neural Networks (NNs). In particular, we tackle an inverse source problem and propose an iterative pruning scheme based on the use of the Singular Value Decomposition (SVD) of weight matrices and bias vectors associated to each layer to reduce the NN complexity. The performance of the approach is shown numerically.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
