Skip to main content
Fig. 4 | BMC Bioinformatics

Fig. 4

From: A biological network-based regularized artificial neural network model for robust phenotype prediction from gene expression data

Fig. 4

Figure depicts average cross validation results in multiple runs of GRRANN (blue) and a randomized version of the model (red), where connections between the hidden and the input nodes are fully shuffled. As can be seen, correct regulatory connections have a significant impact on model performance. Same regularization settings were utilized in both tests

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us