Hacker News Reader

Training examples are unlikely to contain non-faces with high-noseness to the sides and high-eyeness in the center, but plenty of pictures with nose to the left, eye in the center, nose to the right, eye in the center.

So there are many examples which increase the weights for faceness detector for pictures with noses on the sides, eye in the center, but there are only a small number of examples which decrease the weights for the said pictures.

View on HN

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.

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.

Reply on news.ycombinator.com