Timeline for Best way to pass distribution estimates as a feature into deep learning
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 18, 2019 at 11:46 | comment | added | JacobJacox | definetly not the easiest but it removes this prior knowledge problem. I would use KL loss.. so you would sample from decoding part with learned parameters then minimize the difference between prior and sampled? | |
| Jul 18, 2019 at 11:36 | comment | added | user3235916 | its not clear to me how a VAE is the easiest or best first choice here. I would always start simple. How doe VAEs get around the problem of training a large number of parameters? They'll also need lots of required cross validation for choosing the dimensionality of the latent space, VAE architecture etc. How well VAEs perform will also really depends on how the outputs of the meta models are distributed and what parts and structure of that distribution are important. For example, if you are using an MSE metric to optimise VAEs and and the tails are important you could run into trouble... | |
| Jul 17, 2019 at 16:21 | comment | added | JacobJacox | I like it, what abount second edit? | |
| Jul 17, 2019 at 14:24 | vote | accept | JacobJacox | ||
| Jul 17, 2019 at 12:42 | history | answered | user3235916 | CC BY-SA 4.0 |