. @mtyka, @quasimondo & @dribnet are producing many amazing images using neural nets:https://twitter.com/dribnet/status/866213727955070976 …
-
Thanks! My main goal is to be able to understand / use the factors of variation. Eg: organisation, generation, etc.https://twitter.com/dribnet/status/857643217730142208 …
I wonder at imposing a sparsity constraint on the latent variables during training, to improve their ease of interpretation.
-
-
interesting - def see trade-off with dim of latent space. above images from 160 dim, so image starts as 160 floats & "smile" is 160d vector.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.