On: Understanding Hinton’s Capsule Networks, Part I: Intuition

[atupis]

And that's why when you eg training CNN for MNIST you usually nudge and rotate numbers so you can get those weird edge cases.

[red75prime → atupis]

I can't imagine a transformation which consistently produces nose-like features to the sides of an eye-like feature () for non-face source image, thus I doubt that the network will be able learn that such an image () is not a face. In the best case it will recognize the image as a tureen.