Now we just need to add a DNN to tune the GP hyperparameters...
Interesting project that uses genetic programming to automatically find high-performing deep network architectures:https://github.com/joeddav/devol
-
-
-
I think a DQN on top of the GP on top of the DNN would work great, personally
End of conversation
New conversation -
-
-
Esto es lo que te decía que había escuchado para NN MLP, parece que ya avanzó un poco
@ArielRossanigoThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Genetic programming has been shown to be much worse than Gaussian processes and many other hyperparameter optimisation methods
-
Can give me an example or bibliography? Thx
End of conversation
New conversation -
-
-
@ChristopheGC my big data project - thought you might be interestedThanks. 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.