view article

Figure 7
CNN representations of the first convolutional layers of AlexNet with two distinct classes (Strong and No crystal). The visual representations indicate that the network extracts uniquely different representations for the two classes.

Journal logoJOURNAL OF
APPLIED
CRYSTALLOGRAPHY
ISSN: 1600-5767
Follow J. Appl. Cryst.
Sign up for e-alerts
Follow J. Appl. Cryst. on Twitter
Follow us on facebook
Sign up for RSS feeds