Autoencoder Based Optimization for Electromagnetics Problems

In this work a novel approach is presented for topology optimization of electromagnetic devices. In particular a surrogate model based on Deep Neural Networks with encoder-decoder architecture is introduced. A first autoencoder learns to represent the input images that describe the topology, i.e., g...

Full description

Bibliographic Details

Published in:	Applied Computational Electromagnetics Society journal Vol. 34; no. 12; p. 1875
Main Authors:	Barmada, S, Fontana, N, Thomopulos, D, Tucci, M
Format:	Journal Article
Language:	English
Published:	Pisa River Publishers 2019
Subjects:	Algorithms Artificial neural networks Encoders-Decoders Network topologies Neural networks Numerical analysis Optimization Topology optimization
ISSN:	1054-4887, 1943-5711
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!