Supplementary Fig. 5: Changes in curvature in contemporary deep convolutional neural network architectures. | Nature Neuroscience

Supplementary Fig. 5: Changes in curvature in contemporary deep convolutional neural network architectures.

From: Perceptual straightening of natural videos

Supplementary Fig. 5

Despite their strong performance in object recognition, none of these architectures straighten natural videos. Circles indicate the median across sequences, error bars representing the 68% confidence interval are smaller than these circles (n = 12 sequences for natural and artificial stimuli, n = 9 sequences for naturalistic ‘contrast’ stimuli). (a) 19-layer VGG architecture34. (b) 19-layer VGG architecture with batch normalization35. (c) 152-layer Residual Network architecture36. (d) 121-layer Dense Network architecture37.

Back to article page