Google A.I. researchers develop alternative architecture for neural networks

Re:Google A.I. researchers develop alternative architecture ... by topynate on Friday November 10, 2017 @12:01PM (#15671205)

Okay, but it sounds like this technique is targeting learning from a limited number of examples. How does it compare on CIFAR 10 when restricted to ten training images per class? That's the sort of thing that you don't even see in benchmarks, because there hasn't been any way to get a handle on the problem.

[ Parent | on HN ]

Re:Google A.I. researchers develop alternative architecture ... by inverse_pi on Friday November 10, 2017 @12:36PM (#15671464)

That is not true. What you're describing is called zero to a few shot learning in the literature and there are specific benchmarks to test this. The author(s) specifically chose to NOT test on these benchmarks and there is no explicit mentions in the paper that they wanted to target a few shot learning.

[ Parent | on HN ]