News for hackers. Stuff that matters.
Re:Understanding Hinton’s Capsule Networks, Part I: Intuition by p1esk on Wednesday November 15, 2017 @02:36PM (#15707039)
So basically there's zero evidence in the paper that capsule networks require fewer training examples, correct?
Re:Understanding Hinton’s Capsule Networks, Part I: Intuition by eref on Saturday November 18, 2017 @06:03PM (#15731154)
I think that is correct because otherwise they would have mentioned it as an outstanding feature of the model. It does require fewer parameters than a CNN to reach the same accuracy.