Skip to main content
Fig. 2 | BMC Bioinformatics

Fig. 2

From: Novel deep learning-based solution for identification of prognostic subgroups in liver cancer (Hepatocellular carcinoma)

Fig. 2

Pseudocode demonstrating the flow of training an autoencoder with LRSC loss. The custom autoencoder is initially trained with an MSE loss in order to predict a bottleneck from which to identify seed centroids and group assignments which can then be used in the LRSC loss during training. After each epoch training with LRSC the centroids and group assignments are updated

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us