Title :
Electromagnetic field parallel computation with a Hopfield neural network
Author :
Kant, Jean-Daniel ; Le Drezen, Jo ; Bigeon, Jean
Author_Institution :
Ecole Nat. Superieure des Telecommun. de Bretagne, Brest, France
fDate :
5/1/1995 12:00:00 AM
Abstract :
In this paper, we study the feasibility of computing the electromagnetic field in real situations with an artificial neural network, in order to speed up computation. Simulations of our method are presented. We also propose an implementation on an efficient hardware parallel architecture
Keywords :
Hopfield neural nets; electromagnetic fields; electrostatics; magnetostatics; parallel processing; Hopfield neural network; artificial neural network; electromagnetic field; hardware parallel architecture; parallel computation; Boundary conditions; Computer architecture; Computer networks; Concurrent computing; Electromagnetic fields; Hardware; Hopfield neural networks; Magnetostatics; Maxwell equations; Parallel architectures;
Journal_Title :
Magnetics, IEEE Transactions on
