Analysis of magnetic domain patterns by a perceptron neural network
Institut de Recherches Subatomiques - 23 rue du Loess, BP 28
F-67037 Strasbourg, Cedex 2, France
2 Laboratoire de Cristallographie - 25 Avenue des Martyrs, BP 166 38042 Grenoble, Cedex 9, France
Accepted: 25 January 2000
It is shown that magnetic bubble films behaviour can be described by using a 2D super-Ising Hamiltonian. Calculated hysteresis curves and magnetic domain patterns are successfully compared with experimental results taken in the literature. The reciprocal problem of finding parameters of the super-Ising model to reproduce computed or experimental magnetic domain pictures is solved by using a perceptron neural network.
PACS: 75.70.Kw – Domain structure (including magnetic bubbles) / 07.05.Mh – Neural networks, fuzzy logic, artificial intelligence
© EDP Sciences, 2000