Re:Evaluating the Search Phase of Neural Architecture Search
by corporateslave5 on Thursday November 21, 2019 @11:09PM
(#21602330)
The problem with neural architecture search is that we don’t know what to optimize on. We need some kind of topological understanding of the data to help build algorithms that can optimize performance. Clearly passing in error rates is not doing the trick
[ Parent
| on HN ]
Re:Evaluating the Search Phase of Neural Architecture Search
by machinelearning on Friday November 22, 2019 @12:57AM
(#21603164)
I agree, I've been thinking about this too. Do you want to work together on this?