Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision | |||
hyper-parameter_tuning [2018/10/17 16:08] admin |
hyper-parameter_tuning [2018/10/31 10:52] (current) admin |
||
---|---|---|---|
Line 317: | Line 317: | ||
GHNs model the topology of an architecture and therefore can predict network performance more accurately than regular hypernetworks and premature early stopping. To perform NAS, we randomly sample architectures and use the validation accuracy of networks with GHN generated weights as the surrogate search signal. GHNs are fast -- they can search nearly 10 times faster than other random search methods on CIFAR-10 and ImageNet. | GHNs model the topology of an architecture and therefore can predict network performance more accurately than regular hypernetworks and premature early stopping. To perform NAS, we randomly sample architectures and use the validation accuracy of networks with GHN generated weights as the surrogate search signal. GHNs are fast -- they can search nearly 10 times faster than other random search methods on CIFAR-10 and ImageNet. | ||
+ | |||
+ | https://ai.googleblog.com/2018/10/introducing-adanet-fast-and-flexible.html?m=1 |