Performance of neural networks in materials science

H. K. D. H. Bhadeshia, R. C. Dimitriu, S. Forsik, J. H. Pak and J. H. Ryu

Abstract

Neural networks are now a prominent feature of materials science with rapid progress in all sectors of the subject. It is premature, however, to claim that the method is established. There are genuine difficulties caused by the often incomplete exploration and publication of models. The assessment presented here is an attempt to compile a loose set of guidelines for maximising the impact of any models that are created, in order to encourage thoroughness in publication to a point where the work can be independently verified.

Materials Science and Technology 25 (2009) 504-510.

Download PDF file of paper

Coalesced	Foam	TWIP	FSW	3D
Texture	Properties	Silicon	Synchrotron	Models
Neural Networks	Creep	Mechanicallly Alloyed	Theses	Retained Austenite