News for hackers. Stuff that matters.

A comment on Generative Teaching Networks: Accelerating Neural Architecture Search. Parent comment

Re:Generative Teaching Networks: Accelerating Neural Archite... by _0ffh on Thursday February 20, 2020 @03:48PM (#22378460)
> Feel free to ask any questions

Hi, thanks for the invitation!

How can you be sure that the synthetic data you generate does not bias the architecture search away from the optimal solution for real data in a way similar to how early truncation of learning biases architecture search towards quick learners, and possibly away from peak performers?

[ Parent | on HN ]
Re:Generative Teaching Networks: Accelerating Neural Archite... by heyitsguay on Thursday February 20, 2020 @08:15PM (#22380175)
Probably just an empirical comparison with other NAS strategies and hand crafted architectures right? The whole area of research is still ruthlessly empirical.
[ Parent | on HN ]