Skip to main content
. 2020 Nov 12;11:5725. doi: 10.1038/s41467-020-19632-w

Fig. 5. Representational consistency decreases irrespective of distance measure.

Fig. 5

Representational consistency decreases with increasing layer depth for both tested DNN architectures, and across multiple ways to measure distances in multivariate population responses (cosine (a), Euclidean distance and unit length pattern-based Euclidean distance (b), and differences in vector norm (c)). Average representational consistency shown for each layer, computed across all pairwise comparisons of network instances (45 comparisons for 10 instances), together with a 95% bootstrapped confidence interval.