Evaluating models without test data (Practical AI #194)
Changelog Master Feed
00:00
Is There a Complex Optimization Problem?
In principle, you could try to do that algorithmically in a way using a Bayesian type approach where you try to get your alphas to go down on every layer. It's a complex optimization problem, but that's what I would recommend. The point is that you want to learn more correlations. Typically, this is trying to do large-scale metal learning,. You'd have to integrate the tool into some sort of process that allows you to look atMore details in the layer and figure out how to tune from that. And there are lots of things people I think want to try.
Transcript
Play full episode
