Improvement of CNN-Based Anisotropic Magnetostatic Field Computation via Adaptive Data Subset Selection - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Magnetics Année : 2022

Improvement of CNN-Based Anisotropic Magnetostatic Field Computation via Adaptive Data Subset Selection

Résumé

A numerical issue arises when we extend the convolutional neural network (CNN) U-net to the anisotropic magnetostatic field computation. The output magnetic field has a significant gradient with respect to the input geometry parameter, which introduces inevitable errors in the training process to degrade the performance of deep learning (DL). To address this issue, the subset selection approach is utilized to divide the whole database into several subsets, where the samples are assigned according to the gradient between the input and output. Then these subsets with different sample densities are combined into a global one. Taking the uniform dataset with the same sample size as a comparison, the influence of subset selection on DL is investigated by comparing the performance of CNN on different datasets. Numerical experiments illustrate that the adaptive subset selection can be employed to improve the accuracy and efficiency of the CNN network.
Fichier non déposé

Dates et versions

hal-03819595 , version 1 (18-10-2022)

Identifiants

Citer

Ruohan Gong, Zuqi Tang. Improvement of CNN-Based Anisotropic Magnetostatic Field Computation via Adaptive Data Subset Selection. IEEE Transactions on Magnetics, 2022, 58 (9), pp.1-4. ⟨10.1109/TMAG.2022.3169081⟩. ⟨hal-03819595⟩
16 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More