Normalized mutual information for common and private variability. For a given $μ$⁠, 100 networks were created by drawing common noise weights $w$ from the corresponding log-normal distribution. The mutual information shown is the average across the 100 networks. For a specified network, the mutual information was calculated by averaging KSG estimates over 100 simulated data sets, each containing 10,000 samples. Finally, for a choice of $(σP,σC)$⁠, mutual information is normalized to the maximum across values of $μ$⁠. (a) Normalized mutual information as a function of $μ$ and private variability (⁠$σC=0.5$⁠). (b) Normalized mutual information as a function of $μ$ and common variability (⁠$σP=0.5$⁠).