Fig. 2: Network biases in the P-NET model based on deterministic input data.
From: Reliable interpretability of biology-inspired deep neural networks
a Experimental approach. b Node importance derived from deterministic inputs (n = 51 replicate networks), where every input feature is perfectly correlated with the target labels. c ROC curves for the original setup (from Fig. 1) and replicate networks. d Comparison of importance scores for deterministic (n = 51 replicate networks) and original input data (n = 51 replicate networks). Boxes display the median value and 25 and 75% quartiles; the whiskers are extended to the most extreme value inside the 1.5-fold interquartile range; dots show outliers.
