Finding hidden regularities in nature: Researchers apply deep learning to X-ray diffraction

X-ray diffraction (XRD) is an essential technique to identify the structures and compositions of newly developed materials. However, XRD patterns consist of multiple peaks, and it is not always possible to judge which ones are relevant to describe the features of the material. Researchers have recently proposed a neural network that uses the auto-encoder technique to permit the in-depth analysis of XRD patterns to reveal features that might not be identified by humans.

from Latest Science News -- ScienceDaily https://ift.tt/VbfW9qH